© 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. 10-RES_POST_32K-OAI
    11. 26347
    Prev
    Next
    INDEX
    Explanations

    proper nouns and certain uncommon characters in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    756
    +0.21
    1.0%
    387
    +0.11
    0.5%
    502
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.21
    0.07
    314
    +0.11
    -0.01
    659
    +0.10
    0.05
    Negative Logits
    ĸļ
    -0.77
     pse
    -0.64
    successfully
    -0.63
    hyde
    -0.60
    */(
    -0.58
     Ced
    -0.58
    stood
    -0.57
    ©¶æ
    -0.57
    NK
    -0.55
    å§
    -0.55
    POSITIVE LOGITS
    oring
    0.77
    ores
    0.72
    ored
    0.69
    urat
    0.68
    unct
    0.66
    ilo
    0.66
    oration
    0.66
    orate
    0.66
    date
    0.65
    ors
    0.61
    Activations Density 0.769%

    No Known Activations