© 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. 27665
    Prev
    Next
    INDEX
    Explanations

    instances of voting and election-related terminology

    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
    121
    +0.14
    0.6%
    631
    +0.11
    0.5%
    702
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    631
    +0.14
    0.04
    31
    +0.11
    0.04
    24
    +0.10
    0.04
    Negative Logits
    alore
    -0.82
     audiences
    -0.78
    href
    -0.73
    topic
    -0.70
    ivas
    -0.67
     grappling
    -0.66
     Scouting
    -0.66
    ifix
    -0.65
    knit
    -0.64
    roots
    -0.64
    POSITIVE LOGITS
     Jill
    0.74
     whichever
    0.70
     wisely
    0.66
     president
    0.64
    yes
    0.64
     illegally
    0.64
     PRESIDENT
    0.63
     winner
    0.63
     ple
    0.62
     whoever
    0.62
    Activations Density 0.963%

    No Known Activations