© 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. 31440
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to beauty and cosmetic enhancements

    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
    161
    +0.11
    0.5%
    555
    +0.10
    0.5%
    435
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.06
    225
    +0.10
    0.05
    575
    +0.09
    0.04
    Negative Logits
    ern
    -0.77
    umar
    -0.76
    overe
    -0.75
    ajor
    -0.73
    ascal
    -0.73
    ership
    -0.72
    ugal
    -0.71
    ensional
    -0.71
    renheit
    -0.71
     Helpful
    -0.70
    POSITIVE LOGITS
     pageant
    1.29
     salon
    1.05
     contestant
    0.88
     contests
    0.87
     queens
    0.86
     cosmetics
    0.84
     contest
    0.83
     routines
    0.82
     contestants
    0.81
     queen
    0.80
    Activations Density 0.427%

    No Known Activations