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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27124
    Prev
    Next
    INDEX
    Explanations

    references to trademarks, copyrights, and related legal information

    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
    617
    +0.12
    0.6%
    467
    +0.10
    0.5%
    3
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.12
    0.03
    767
    +0.10
    0.02
    711
    +0.10
    0.01
    Negative Logits
     Inquiry
    -0.69
    iless
    -0.68
     defund
    -0.65
    aghetti
    -0.63
    Reviewer
    -0.62
     Aid
    -0.62
    watching
    -0.60
    asar
    -0.60
    bugs
    -0.59
    jar
    -0.59
    POSITIVE LOGITS
     trademarks
    1.37
     trademark
    1.22
     registered
    1.16
     tradem
    1.13
     logos
    1.06
     Trad
    1.00
     marks
    0.86
     brands
    0.85
     distinctive
    0.85
     registrations
    0.84
    Activations Density 0.495%

    No Known Activations