© 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. 27694
    Prev
    Next
    INDEX
    Explanations

    references to hyperlinks or links in a document

    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
    446
    +0.11
    0.5%
    701
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.11
    0.02
    711
    +0.11
    0.01
    701
    +0.10
    0.01
    Negative Logits
    nces
    -0.81
     captcha
    -0.74
     Liberties
    -0.73
    ÅŁ
    -0.65
     Croat
    -0.62
    iren
    -0.62
    oured
    -0.61
     Scotia
    -0.61
    issance
    -0.60
    mble
    -0.59
    POSITIVE LOGITS
    edin
    1.26
    ages
    1.16
    later
    1.15
    erd
    0.89
    age
    0.89
    witz
    0.86
    er
    0.86
    ern
    0.82
    ery
    0.79
    letter
    0.77
    Activations Density 0.152%

    No Known Activations