© 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. 10145
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bat"

    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
    156
    +0.48
    3.4%
    111
    +0.42
    3.0%
    271
    +0.17
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    205
    +0.48
    0.44
    40
    +0.42
    0.40
    428
    +0.17
    0.37
    Negative Logits
    ↵
    -4.08
     ↵
    -4.08
    ↵↵
    -4.08
    -4.08
    <|outofrange|>
    -4.08
    ↵↵
    -4.08
     ↵
    -4.08
    -4.08
    ↵↵
    -4.08
    č↵
    -4.08
    POSITIVE LOGITS
    TRODUCTION
    1.70
    rosis
    1.56
    TEGER
    1.55
    olia
    1.50
    ella
    1.47
    idad
    1.39
    umab
    1.31
    elles
    1.31
    ria
    1.28
    ucci
    1.25
    Activations Density 0.816%

    No Known Activations