© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3503
    Prev
    Next
    INDEX
    Explanations

    error messages or indications of problems in a programming context

    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
    207
    +0.11
    0.5%
    402
    +0.10
    0.4%
    451
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.05
    381
    +0.10
    0.04
    345
    +0.09
    0.04
    Negative Logits
    ',"
    -0.78
     itch
    -0.74
    obyl
    -0.71
     craving
    -0.71
    tails
    -0.69
    acea
    -0.67
    ,'"
    -0.66
    ourke
    -0.65
    ":[{"
    -0.64
     headaches
    -0.63
    POSITIVE LOGITS
     Kills
    0.78
    LU
    0.73
     Fortress
    0.73
    LV
    0.68
    Mil
    0.65
    cipl
    0.64
    LIB
    0.64
     ......
    0.64
     Municipal
    0.64
    Military
    0.63
    Activations Density 0.732%

    No Known Activations