© 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. 10223
    Prev
    Next
    INDEX
    Explanations

    explicit content related to adult themes and sexual activities

    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
    319
    +0.14
    0.8%
    338
    +0.12
    0.7%
    17
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.14
    0.08
    338
    +0.12
    0.03
    414
    +0.12
    0.11
    Negative Logits
    §
    -3.96
    ī
    -3.92
    ĸ
    -3.90
    İ
    -3.73
    Ł
    -3.73
    ¯
    -3.72
    ↵↵
    -3.67
                  ↵
    -3.67
    <|outofrange|>
    -3.67
    <|outofrange|>
    -3.67
    POSITIVE LOGITS
     porn
    4.31
     sex
    4.21
     erotic
    4.19
     Sex
    4.10
     sexual
    3.98
     orgasm
    3.84
     nude
    3.77
     sexually
    3.74
     pussy
    3.63
     anal
    3.58
    Activations Density 3.299%

    No Known Activations