© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 8787
    Prev
    Next
    INDEX
    Explanations

    expressions or words related to specific names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    249
    +0.10
    0.5%
    533
    +0.10
    0.5%
    354
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    740
    +0.10
    0.10
    426
    +0.10
    0.09
    514
    +0.10
    0.09
    Negative Logits
     ancest
    -0.69
     permissible
    -0.63
    udic
    -0.63
    accompan
    -0.63
     Miscellaneous
    -0.62
     mathemat
    -0.61
    arij
    -0.60
    è¦ļéĨĴ
    -0.59
    isma
    -0.59
    isine
    -0.58
    POSITIVE LOGITS
     Yen
    1.05
    cha
    0.82
    ue
    0.76
     Kong
    0.74
    zos
    0.74
    tin
    0.72
    ibles
    0.71
    inho
    0.70
    ye
    0.68
    combe
    0.66
    Activations Density 0.631%

    No Known Activations