© 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. 13882
    Prev
    Next
    INDEX
    Explanations

    roles or identities related to specific professions and interests

    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
    +0.17
    1.0%
    156
    +0.16
    0.9%
    288
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.17
    0.10
    233
    +0.16
    0.06
    288
    +0.15
    0.11
    Negative Logits
    ↵↵
    -9.78
    -9.78
    <|outofrange|>
    -9.78
    <|outofrange|>
    -9.78
    -9.78
    ↵↵↵
    -9.78
     ↵
    -9.78
    <|outofrange|>
    -9.78
    <|outofrange|>
    -9.78
    ↵
    -9.78
    POSITIVE LOGITS
     who
    2.35
     myself
    2.31
     believer
    2.19
     capable
    2.09
    maid
    2.04
     minded
    1.97
     willing
    1.96
    iac
    1.96
    izer
    1.95
    opher
    1.95
    Activations Density 1.587%

    No Known Activations