© 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. 9346
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals

    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
    382
    +0.14
    0.8%
    57
    +0.13
    0.7%
    6
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.14
    0.06
    165
    +0.13
    0.06
    410
    +0.13
    0.05
    Negative Logits
    OOGLE
    -1.66
     where
    -1.66
    /~
    -1.64
    youtube
    -1.56
    :-
    -1.51
    ”.
    -1.50
    bserver
    -1.50
    where
    -1.49
    arcelona
    -1.49
     ago
    -1.48
    POSITIVE LOGITS
     Randolph
    2.07
     Williamson
    2.00
     Eugene
    1.98
     Gardner
    1.97
     Anthony
    1.96
     Doe
    1.96
     Mc
    1.95
     Dunn
    1.92
     Davis
    1.92
     Lee
    1.91
    Activations Density 0.218%

    No Known Activations