© 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. 3527
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" and various numerical or categorical indicators

    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
    71
    +0.14
    0.6%
    109
    +0.12
    0.6%
    69
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.14
    0.01
    69
    +0.12
    0.01
    45
    +0.12
    0.00
    Negative Logits
    paren
    -0.71
     toget
    -0.70
    ascript
    -0.69
     databases
    -0.68
     surprises
    -0.66
    ridges
    -0.65
    otally
    -0.65
    fing
    -0.64
    rows
    -0.64
     pauses
    -0.64
    POSITIVE LOGITS
     mantle
    0.71
    èĢħ
    0.70
    é¾į
    0.70
     Zup
    0.69
     Rend
    0.67
    æĸ¹
    0.66
    ulkan
    0.62
     partName
    0.60
    DEM
    0.59
     centerpiece
    0.59
    Activations Density 0.029%

    No Known Activations