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. 6444
    Prev
    Next
    INDEX
    Explanations

    structural indicators related to clarity and categorization within documents

    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
    549
    +0.19
    1.2%
    568
    +0.17
    1.1%
    442
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.19
    -0.00
    724
    +0.17
    0.04
    720
    +0.16
    0.04
    Negative Logits
    ccording
    -0.73
    owler
    -0.69
     coma
    -0.69
     ensemble
    -0.68
     birthday
    -0.65
     pollut
    -0.65
     circus
    -0.64
    bably
    -0.64
     park
    -0.63
    ön
    -0.63
    POSITIVE LOGITS
    anamo
    0.93
    Downloadha
    0.89
    士
    0.86
    asus
    0.82
    ricular
    0.80
    aterasu
    0.76
    awei
    0.74
    advertising
    0.73
    ilon
    0.72
    artifacts
    0.72
    Activations Density 0.047%

    No Known Activations