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. 6447
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bet" and its variations used in various contexts

    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
    283
    +0.30
    2.2%
    718
    +0.21
    1.5%
    274
    +0.19
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.30
    0.02
    187
    +0.21
    0.02
    718
    +0.19
    0.01
    Negative Logits
    ugu
    -0.90
    hammad
    -0.85
    NetMessage
    -0.85
    avorite
    -0.84
    odore
    -0.79
    isms
    -0.78
    ulhu
    -0.78
    ebin
    -0.74
    İĭ
    -0.73
    istry
    -0.72
    POSITIVE LOGITS
    mitt
    0.76
    enegger
    0.69
    peak
    0.68
     Gry
    0.68
    meter
    0.66
    Scot
    0.66
    beat
    0.64
    ãĤ£
    0.64
     Rouse
    0.63
     IRA
    0.62
    Activations Density 0.063%

    No Known Activations