© 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. 3789
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationships or connections over time

    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
    745
    +0.21
    1.0%
    311
    +0.11
    0.5%
    168
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    745
    +0.21
    0.22
    554
    +0.11
    0.23
    87
    +0.10
    -0.17
    Negative Logits
     vacated
    -0.63
    hiba
    -0.62
    ONSORED
    -0.60
     branches
    -0.60
     accessed
    -0.60
     collapsed
    -0.59
     itself
    -0.59
    tnc
    -0.58
    opl
    -0.57
     driveway
    -0.57
    POSITIVE LOGITS
     handwriting
    0.77
    VIDIA
    0.76
    hemy
    0.71
    pmwiki
    0.70
    olean
    0.69
    itaire
    0.68
    ãĥ¯ãĥ³
    0.64
    ãĤ¤ãĥĪ
    0.63
    ©¶æ¥µ
    0.62
     VIDE
    0.62
    Activations Density 10.428%

    No Known Activations