© 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 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. 31057
    Prev
    Next
    INDEX
    Explanations

    HTML formatting elements and metadata

    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
    373
    +0.17
    0.8%
    37
    +0.12
    0.6%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.17
    0.01
    373
    +0.12
    -0.03
    555
    +0.11
    0.02
    Negative Logits
     coerc
    -0.67
    sembly
    -0.62
     dismant
    -0.61
     disposable
    -0.59
    illance
    -0.59
     forfe
    -0.58
    obyl
    -0.57
     largeDownload
    -0.57
     desper
    -0.57
     respir
    -0.57
    POSITIVE LOGITS
    description
    0.79
    iversary
    0.77
    thumbnails
    0.76
    src
    0.71
    published
    0.69
    credit
    0.68
    stream
    0.68
    authors
    0.68
    author
    0.68
    year
    0.67
    Activations Density 0.211%

    No Known Activations