© 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. 27635
    Prev
    Next
    INDEX
    Explanations

    words related to commenting and comments in a discussion context

    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
    575
    +0.11
    0.5%
    756
    +0.11
    0.5%
    424
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.11
    0.04
    424
    +0.11
    0.03
    175
    +0.11
    0.02
    Negative Logits
    icz
    -0.85
     Sinai
    -0.76
     Metatron
    -0.67
    YP
    -0.65
    lay
    -0.64
    INO
    -0.63
     Ethiopian
    -0.63
     pilgr
    -0.62
     Cov
    -0.62
     Eston
    -0.61
    POSITIVE LOGITS
    ariat
    1.33
    aries
    1.19
    ature
    0.94
    ators
    0.93
    arial
    0.92
    area
    0.88
    aires
    0.87
    atively
    0.84
     sections
    0.84
    oras
    0.82
    Activations Density 0.198%

    No Known Activations