© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    expressions of need and collective action in various contexts

    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
    502
    +0.12
    0.5%
    475
    +0.12
    0.5%
    713
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.12
    0.15
    713
    +0.12
    0.14
    502
    +0.12
    0.14
    Negative Logits
     overshadowed
    -0.68
    Downloadha
    -0.63
    stroke
    -0.63
     accompanied
    -0.62
     exerc
    -0.62
     Solitaire
    -0.61
    cre
    -0.61
    allo
    -0.60
    stro
    -0.60
     CRC
    -0.59
    POSITIVE LOGITS
     ourselves
    1.53
     our
    0.89
     OUR
    0.77
    Our
    0.75
     Our
    0.67
     Pledge
    0.67
     ours
    0.65
     asses
    0.65
     Eag
    0.64
    chat
    0.63
    Activations Density 8.200%

    No Known Activations