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

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    11. 4266
    Prev
    Next
    INDEX
    Explanations

    references to updates and news information

    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
    465
    +0.12
    0.6%
    713
    +0.11
    0.5%
    230
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.12
    0.10
    731
    +0.11
    0.07
    103
    +0.11
    0.11
    Negative Logits
    TERN
    -0.81
    atern
    -0.77
     Syndicate
    -0.72
     insurrection
    -0.69
     TR
    -0.69
     Trudeau
    -0.69
    Sync
    -0.68
    TN
    -0.67
    lihood
    -0.67
     TAG
    -0.67
    POSITIVE LOGITS
    ifer
    0.80
    innie
    0.79
    ife
    0.79
    gart
    0.77
    licts
    0.74
    ovie
    0.74
     dr
    0.72
    azel
    0.72
    elope
    0.72
    kee
    0.71
    Activations Density 3.382%

    No Known Activations