Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 128k
    5. 0-ATT_128K-OAI
    6. 6440
    Prev
    Next
    INDEX
    Explanations

    references to sports and entertainment figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/GPT2-Small-OAI-v5-128k-attn-out-SAEs/v5_128k_layer_0
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    131,072
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_attn_out
    Hook Layer
    0
    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
    442
    +0.17
    1.2%
    285
    +0.14
    0.9%
    659
    +0.13
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.02
    434
    +0.14
    0.06
    659
    +0.13
    0.01
    Negative Logits
    taboola
    -0.99
     rall
    -0.79
     Discuss
    -0.77
    eers
    -0.75
    Results
    -0.74
    Versions
    -0.74
     kcal
    -0.72
    Rect
    -0.72
    VERTISEMENT
    -0.72
     Assembly
    -0.72
    POSITIVE LOGITS
    assetsadobe
    0.91
    dinand
    0.89
    abit
    0.89
    bats
    0.86
    ady
    0.82
    wolves
    0.81
    pless
    0.79
    wed
    0.77
    pell
    0.76
    ipeg
    0.74
    Activations Density 5.054%

    No Known Activations