© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and identifiers

    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
    218
    +0.18
    0.8%
    423
    +0.10
    0.5%
    452
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.18
    0.02
    566
    +0.10
    0.02
    326
    +0.10
    0.02
    Negative Logits
     Gamble
    -0.81
    entanyl
    -0.74
    EAR
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.70
    Pur
    -0.66
     Gram
    -0.64
     PUR
    -0.63
    onics
    -0.61
     impressions
    -0.61
     VG
    -0.61
    POSITIVE LOGITS
    etheless
    0.71
    luaj
    0.67
    respect
    0.67
    hawk
    0.67
     obstruction
    0.66
     compromised
    0.63
    Conclusion
    0.62
     somew
    0.62
    arent
    0.60
    endif
    0.60
    Activations Density 0.073%

    No Known Activations