© 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. 4-RES-SM
    11. 8956
    Prev
    Next
    INDEX
    Explanations

    details related to physical attributes and capabilities

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.34
    2.0%
    156
    +0.23
    1.4%
    63
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.34
    0.08
    450
    +0.23
    0.03
    73
    +0.11
    0.12
    Negative Logits
    ĥ½
    -3.62
    ↵↵
    -3.50
    ↵↵
    -3.50
    <|outofrange|>
    -3.50
    ↵
    -3.50
    -3.50
    -3.50
    ↵↵
    -3.50
    -3.50
    <|outofrange|>
    -3.50
    POSITIVE LOGITS
     he
    3.41
     his
    3.35
    \]\].
    3.19
     himself
    3.12
     */
    3.06
     His
    2.96
     He
    2.90
     him
    2.86
    )\].
    2.80
    His
    2.74
    Activations Density 3.960%

    No Known Activations