© 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 EvalsExportsinterp-engineNEWAPI 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. 25301
    Prev
    Next
    INDEX
    Explanations

    fragments of data representing numerical values and configurations, potentially related to technical specifications or settings

    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
    69
    +0.14
    0.8%
    84
    +0.12
    0.7%
    448
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.14
    0.05
    16
    +0.12
    0.06
    124
    +0.12
    0.06
    Negative Logits
     expectation
    -1.68
     (*
    -1.54
     isolation
    -1.49
     tolerance
    -1.46
     disbelief
    -1.44
     receiving
    -1.38
     respondent
    -1.38
    leave
    -1.38
    \"
    -1.36
     hope
    -1.36
    POSITIVE LOGITS
    ¸
    2.12
    Ĥ¬
    1.88
    »
    1.86
    Verlag
    1.86
    ski
    1.80
    »¿
    1.77
    IJ
    1.70
    ¢
    1.68
    lish
    1.68
    ¼
    1.67
    Activations Density 0.280%

    No Known Activations