© 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. 8-RES_POST_32K-OAI
    11. 7515
    Prev
    Next
    INDEX
    Explanations

    references to specific the names and affiliations of people 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
    482
    +0.10
    0.4%
    363
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.11
    314
    +0.09
    -0.02
    48
    +0.09
    0.07
    Negative Logits
     Butter
    -0.85
     Benz
    -0.82
     para
    -0.81
     paperback
    -0.76
     TA
    -0.75
     Tiny
    -0.74
     Za
    -0.74
     Tablet
    -0.74
     Paper
    -0.73
     Tec
    -0.71
    POSITIVE LOGITS
    org
    0.92
    STEM
    0.86
    agn
    0.80
    rouse
    0.79
    ENG
    0.77
    Hug
    0.77
    uh
    0.74
    Rus
    0.73
    ih
    0.73
    irc
    0.73
    Activations Density 2.993%

    No Known Activations