© 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. 3932
    Prev
    Next
    INDEX
    Explanations

    mentions of severe conditions or significant incidents

    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
    481
    +0.18
    0.8%
    420
    +0.13
    0.6%
    660
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.18
    0.25
    447
    +0.13
    0.25
    660
    +0.11
    0.13
    Negative Logits
     Reloaded
    -0.80
    enhagen
    -0.79
    successfully
    -0.75
    âĹ¼
    -0.73
    ktop
    -0.69
    hov
    -0.67
     [|
    -0.67
    undai
    -0.66
    veland
    -0.66
     Answers
    -0.65
    POSITIVE LOGITS
     disposition
    0.83
     careg
    0.77
    rious
    0.76
    eness
    0.70
    ience
    0.70
     presence
    0.70
     lie
    0.68
     substance
    0.67
    idious
    0.67
    esthetic
    0.67
    Activations Density 14.415%

    No Known Activations