© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3837
    Prev
    Next
    INDEX
    Explanations

    references to statistical or numerical data

    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
    565
    +0.11
    0.5%
    279
    +0.11
    0.5%
    479
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.11
    0.12
    64
    +0.11
    -0.17
    756
    +0.10
    0.16
    Negative Logits
    colo
    -0.86
     Ital
    -0.68
    inline
    -0.60
     OW
    -0.59
     Mei
    -0.59
     Ez
    -0.58
     mural
    -0.58
    LET
    -0.57
    pedia
    -0.56
    oren
    -0.56
    POSITIVE LOGITS
    TPPStreamerBot
    0.77
    )].
    0.71
    whatever
    0.70
    EStreamFrame
    0.68
    rats
    0.68
    [/
    0.68
     Reincarn
    0.67
    untu
    0.67
     [/
    0.63
    çī
    0.63
    Activations Density 11.167%

    No Known Activations