© 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. 4176
    Prev
    Next
    INDEX
    Explanations

    elements of emphasis or intensity within the text

    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
    314
    +0.17
    0.8%
    373
    +0.13
    0.6%
    564
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.17
    0.17
    107
    +0.13
    0.16
    48
    +0.11
    0.13
    Negative Logits
     Conversion
    -0.81
     conversions
    -0.77
     conversion
    -0.75
     Entered
    -0.73
     outnumbered
    -0.72
     Amend
    -0.72
     valued
    -0.69
     Decoder
    -0.69
     Init
    -0.68
     Lauder
    -0.67
    POSITIVE LOGITS
    insert
    1.19
    sn
    1.13
    laughs
    1.12
    gr
    1.03
    shock
    1.03
    sp
    1.02
    cue
    1.01
    fac
    0.99
    added
    0.99
    kiss
    0.97
    Activations Density 1.333%

    No Known Activations