© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3663
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" to identify conjunctions connecting ideas

    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
    245
    +0.10
    0.4%
    689
    +0.10
    0.4%
    419
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    661
    +0.10
    0.05
    214
    +0.10
    0.04
    721
    +0.09
    0.03
    Negative Logits
     Bucc
    -0.87
     DeV
    -0.72
     Blow
    -0.70
     IMAGES
    -0.69
     Prediction
    -0.67
     Subtle
    -0.66
    Pierre
    -0.66
    istical
    -0.64
     Masquerade
    -0.63
     Doll
    -0.62
    POSITIVE LOGITS
    eeper
    0.78
    âĹ¼
    0.77
     arbitration
    0.77
    ãĤ¸
    0.70
    mere
    0.69
     forgiveness
    0.69
    displayText
    0.68
    âĶĢâĶĢâĶĢâĶĢ
    0.67
    abiding
    0.65
     waivers
    0.65
    Activations Density 0.815%

    No Known Activations