© 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. 3768
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, particularly those starting with "St" or related to Saint names

    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
    415
    +0.11
    0.5%
    257
    +0.10
    0.5%
    601
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.11
    0.05
    257
    +0.10
    0.04
    415
    +0.10
    0.05
    Negative Logits
    ãĥ¤
    -0.83
    cffffcc
    -0.78
    ãĥ¼ãĥ³
    -0.75
     jewels
    -0.73
    ¿½
    -0.69
     Wonderland
    -0.67
     trickle
    -0.67
    ãĥīãĥ©
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    querque
    -0.64
    POSITIVE LOGITS
    adder
    0.85
    warts
    0.82
    finding
    0.77
    ousse
    0.75
    wart
    0.73
    bard
    0.72
    Pierre
    0.70
    wick
    0.68
    oller
    0.67
    inus
    0.67
    Activations Density 1.670%

    No Known Activations