© 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. 10-RES_POST_32K-OAI
    11. 29439
    Prev
    Next
    INDEX
    Explanations

    words related to legal and judicial terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    362
    +0.15
    0.7%
    373
    +0.13
    0.6%
    385
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.15
    0.12
    45
    +0.13
    0.09
    284
    +0.10
    0.10
    Negative Logits
    inus
    -0.91
    ère
    -0.85
    enough
    -0.83
    abulary
    -0.83
    iries
    -0.82
    ini
    -0.82
    itten
    -0.81
    erie
    -0.81
    adh
    -0.81
    ioned
    -0.81
    POSITIVE LOGITS
     Educ
    0.80
     Reform
    0.78
     Investig
    0.76
     los
    0.73
     tr
    0.72
     Est
    0.70
     Elev
    0.69
     Inform
    0.69
     Tec
    0.69
     Conver
    0.68
    Activations Density 0.866%

    No Known Activations