© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3957
    Prev
    Next
    INDEX
    Explanations

    references to studies or investigations related to larger contexts or populations

    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
    17
    +0.13
    0.6%
    20
    +0.11
    0.5%
    207
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.13
    0.04
    724
    +0.11
    0.04
    322
    +0.10
    0.04
    Negative Logits
    ception
    -0.79
    modern
    -0.74
     Samar
    -0.67
    clusive
    -0.62
    mopolitan
    -0.61
    aire
    -0.60
     Peb
    -0.59
     Secure
    -0.59
     Ãľ
    -0.59
    fb
    -0.59
    POSITIVE LOGITS
     reluct
    0.91
     proport
    0.83
    ãĤ¨ãĥ«
    0.76
     recons
    0.76
    inventoryQuantity
    0.75
    ĸļ
    0.75
     eleph
    0.73
     tiss
    0.70
     conclud
    0.70
     challeng
    0.69
    Activations Density 1.107%

    No Known Activations