© 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. 27127
    Prev
    Next
    INDEX
    Explanations

    various forms of web addresses and links

    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
    497
    +0.12
    0.5%
    39
    +0.12
    0.5%
    177
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.04
    232
    +0.12
    0.05
    515
    +0.09
    0.03
    Negative Logits
    lehem
    -0.70
     summ
    -0.69
    pez
    -0.67
     affili
    -0.65
    iries
    -0.64
     absentee
    -0.63
     grandson
    -0.63
     telephone
    -0.62
    gypt
    -0.62
     pawn
    -0.61
    POSITIVE LOGITS
    tv
    1.19
    org
    1.15
    io
    1.10
    com
    0.99
    net
    0.87
    IO
    0.83
    shown
    0.82
     Supports
    0.80
    Apps
    0.78
    demon
    0.74
    Activations Density 0.374%

    No Known Activations