© 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. 32459
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "pepper" and variations related to it

    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
    314
    +0.12
    0.5%
    35
    +0.10
    0.4%
    545
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.04
    99
    +0.10
    0.02
    461
    +0.09
    0.02
    Negative Logits
    raped
    -0.66
    hematic
    -0.65
    ADRA
    -0.65
    YA
    -0.63
     singular
    -0.60
    UE
    -0.60
     Reincarn
    -0.59
     Ryzen
    -0.59
    ür
    -0.58
    orem
    -0.58
    POSITIVE LOGITS
    mint
    1.82
    oni
    1.25
    onis
    1.10
    idge
    1.04
    ity
    0.86
    illo
    0.85
    spr
    0.80
    anto
    0.80
    vine
    0.79
    sea
    0.79
    Activations Density 0.231%

    No Known Activations