© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    terms related to government regulation and oversight

    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
    756
    +0.14
    0.6%
    481
    +0.13
    0.6%
    419
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.14
    0.12
    481
    +0.13
    0.17
    711
    +0.12
    0.07
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    ciation
    -0.74
    é¾
    -0.73
     Carbuncle
    -0.73
     Hodg
    -0.69
     Ryder
    -0.69
     Deus
    -0.67
     Rapt
    -0.67
     Rabbit
    -0.65
     Gallagher
    -0.65
    POSITIVE LOGITS
     lawfully
    0.89
    illegal
    0.82
     unlawfully
    0.77
    iaries
    0.75
    disabled
    0.71
     illegally
    0.71
    sites
    0.70
     improperly
    0.68
     adversely
    0.68
    eligible
    0.67
    Activations Density 6.444%

    No Known Activations