© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political contexts

    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
    373
    +0.12
    0.6%
    181
    +0.10
    0.5%
    120
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.09
    314
    +0.10
    -0.01
    288
    +0.10
    0.10
    Negative Logits
    âĢķ
    -0.93
     ______
    -0.81
     whilst
    -0.80
     ðŁĻĤ
    -0.79
     etc
    -0.77
    ̶
    -0.74
     (<
    -0.71
     Cthulhu
    -0.70
    âĢ¦
    -0.70
     EVERY
    -0.69
    POSITIVE LOGITS
     spokeswoman
    1.32
     spokesman
    1.28
     officials
    1.10
     campaigners
    1.05
     spokesperson
    1.03
    earchers
    0.95
     activists
    0.95
     analysts
    0.94
     lawmakers
    0.93
     experts
    0.91
    Activations Density 1.329%

    No Known Activations