© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4032
    Prev
    Next
    INDEX
    Explanations

    references to male individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    408
    +0.10
    0.4%
    131
    +0.10
    0.4%
    451
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.10
    0.02
    425
    +0.10
    0.04
    472
    +0.09
    0.03
    Negative Logits
    ADVERTISEMENT
    -0.85
    âĢ³
    -0.75
    âĢ²
    -0.74
    Nav
    -0.73
    SET
    -0.73
    Ct
    -0.72
    RET
    -0.71
    set
    -0.67
    ãĢı
    -0.67
     Accounts
    -0.65
    POSITIVE LOGITS
     prostitution
    0.75
     slurs
    0.72
    ModLoader
    0.71
     penetrating
    0.69
     prostitutes
    0.68
     jails
    0.67
     semen
    0.67
     surn
    0.65
    agher
    0.64
     psychiatrists
    0.62
    Activations Density 1.204%

    No Known Activations