© 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. 1-RES-SM
    11. 28065
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting indicators

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    495
    +0.14
    0.8%
    369
    +0.14
    0.8%
    285
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.14
    0.00
    349
    +0.14
    0.00
    283
    +0.13
    0.00
    Negative Logits
    Īĺ
    -2.33
    Ĭ
    -2.10
    «
    -2.05
    Ķ
    -2.00
    ĥ
    -1.83
    Ģ
    -1.80
    Ł
    -1.77
    ļ
    -1.73
    ®
    -1.72
    »¿
    -1.71
    POSITIVE LOGITS
     msgid
    1.65
    ---|
    1.55
     else
    1.49
    ulp
    1.44
    hip
    1.43
    ui
    1.43
    MODULE
    1.42
     (,
    1.41
    gradle
    1.39
    /.
    1.37
    Activations Density 0.000%

    No Known Activations