© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 29664
    Prev
    Next
    INDEX
    Explanations

    words associated with technical processes and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    365
    +0.14
    0.8%
    227
    +0.12
    0.7%
    271
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.14
    0.06
    292
    +0.12
    0.12
    335
    +0.11
    0.12
    Negative Logits
     similarities
    -1.72
    ¹
    -1.48
     trends
    -1.48
     liabilities
    -1.38
     plenty
    -1.34
     closely
    -1.33
     anomalies
    -1.33
     appearances
    -1.31
     indications
    -1.30
     crew
    -1.29
    POSITIVE LOGITS
    -------------------------------------------------------
    1.64
    attention
    1.64
    áĢ¬
    1.57
    ------------------------------------------------------
    1.55
    ãĤį
    1.55
    ----------------------------------------------------
    1.49
    ---------------------------------------------------
    1.44
    ainer
    1.41
    --------------------------------------------------
    1.41
    entre
    1.39
    Activations Density 4.996%

    No Known Activations