© 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. 3895
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    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
    298
    +0.10
    0.5%
    607
    +0.10
    0.4%
    246
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.10
    0.04
    765
    +0.10
    0.04
    757
    +0.10
    0.05
    Negative Logits
    writers
    -0.73
     Bulk
    -0.67
     Archive
    -0.67
    notations
    -0.65
    berus
    -0.65
    ilings
    -0.64
     LIMITED
    -0.64
    eway
    -0.63
    ippers
    -0.62
     Annotations
    -0.62
    POSITIVE LOGITS
    addons
    0.75
     fires
    0.74
     menstrual
    0.68
     anten
    0.65
     diaper
    0.65
    iever
    0.65
     deprivation
    0.64
     immoral
    0.64
     defiant
    0.63
    Occup
    0.63
    Activations Density 1.027%

    No Known Activations