© 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. 3689
    Prev
    Next
    INDEX
    Explanations

    references to lobbying activities within healthcare and 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
    340
    +0.11
    0.5%
    481
    +0.10
    0.5%
    168
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.11
    0.03
    417
    +0.10
    0.03
    12
    +0.09
    0.03
    Negative Logits
    thumbnails
    -0.68
     Locked
    -0.68
     LC
    -0.63
     rehearsal
    -0.61
    Ö¼
    -0.61
     Heist
    -0.60
    Ö
    -0.60
     Karma
    -0.60
     Revelations
    -0.59
     ecstasy
    -0.57
    POSITIVE LOGITS
     appropri
    0.77
    ete
    0.76
    uate
    0.74
     wa
    0.74
    amaru
    0.74
     inclusion
    0.73
    enta
    0.73
    olulu
    0.72
    odo
    0.70
     reconsider
    0.69
    Activations Density 0.363%

    No Known Activations