© 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. 13706
    Prev
    Next
    INDEX
    Explanations

    numeric values related to financial amounts and statistics

    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
    324
    +0.11
    0.6%
    500
    +0.11
    0.6%
    373
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.11
    0.07
    485
    +0.11
    0.05
    373
    +0.10
    0.09
    Negative Logits
    ©
    -3.06
    ¢
    -2.83
    ·¸
    -2.54
    -2.54
    -2.54
    <|outofrange|>
    -2.54
    ↵↵
    -2.54
    -2.54
    -2.54
    -2.54
    POSITIVE LOGITS
     200
    2.70
     400
    2.65
     300
    2.64
     250
    2.61
     500
    2.59
     800
    2.51
     150
    2.45
     600
    2.44
     100
    2.41
     350
    2.39
    Activations Density 1.735%

    No Known Activations