© 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. 31932
    Prev
    Next
    INDEX
    Explanations

    quotations and dialogue in the text

    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
    86
    +0.21
    1.0%
    737
    +0.11
    0.5%
    29
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.21
    0.09
    160
    +0.11
    0.09
    6
    +0.10
    0.08
    Negative Logits
     FIG
    -0.72
     corp
    -0.71
     avatar
    -0.71
     caster
    -0.70
     towed
    -0.68
    tein
    -0.66
     semen
    -0.65
    uo
    -0.64
     perpendicular
    -0.64
     zo
    -0.64
    POSITIVE LOGITS
    Tonight
    1.23
    America
    1.12
    Americans
    1.08
    Republicans
    1.05
    Enough
    1.05
    Let
    1.02
    Today
    1.01
    President
    0.98
    Secretary
    0.98
    Democrats
    0.98
    Activations Density 0.260%

    No Known Activations