© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5682
    Prev
    Next
    INDEX
    Explanations

    references to specific political figures or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    148
    +0.13
    0.6%
    50
    +0.11
    0.5%
    571
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.13
    0.01
    738
    +0.11
    0.02
    232
    +0.11
    0.03
    Negative Logits
    dor
    -0.74
    displayText
    -0.74
     coli
    -0.66
    aucas
    -0.65
    united
    -0.63
    inguished
    -0.61
    axter
    -0.61
    arij
    -0.61
     coron
    -0.61
     borough
    -0.60
    POSITIVE LOGITS
     chops
    0.82
     Sell
    0.70
     versatility
    0.64
     Winning
    0.63
     amplify
    0.63
    formance
    0.60
    ousse
    0.60
    Export
    0.58
     agility
    0.58
    amins
    0.57
    Activations Density 0.232%

    No Known Activations