© 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. 3775
    Prev
    Next
    INDEX
    Explanations

    references to specific legal or legislative actions related to public policy

    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
    752
    +0.13
    0.6%
    620
    +0.09
    0.4%
    127
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.13
    0.14
    127
    +0.09
    0.10
    752
    +0.09
    0.14
    Negative Logits
     ..........
    -0.83
    enum
    -0.82
     Seymour
    -0.71
    ouver
    -0.67
     Edwin
    -0.65
     ``
    -0.65
     Tycoon
    -0.63
     wise
    -0.62
    icably
    -0.61
    atu
    -0.61
    POSITIVE LOGITS
    Downloadha
    0.83
    phas
    0.68
     playlist
    0.66
     inclusive
    0.65
     competitions
    0.63
     kits
    0.63
    beta
    0.61
    bush
    0.61
     renewables
    0.60
    senal
    0.60
    Activations Density 10.325%

    No Known Activations