© 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. 28616
    Prev
    Next
    INDEX
    Explanations

    references to validity and existence of information, as well as indications of negation

    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
    386
    +0.11
    0.5%
    244
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    631
    +0.11
    0.01
    127
    +0.10
    0.01
    Negative Logits
    ESSION
    -0.73
     cass
    -0.71
    FUL
    -0.70
    record
    -0.69
    intosh
    -0.69
    anguage
    -0.65
    terday
    -0.65
    oice
    -0.65
    icip
    -0.63
    caster
    -0.63
    POSITIVE LOGITS
     dstg
    0.76
     ticking
    0.63
    culated
    0.61
     unloaded
    0.60
    Occup
    0.56
     looted
    0.56
    ¥µ
    0.56
     reused
    0.56
     sourced
    0.55
    bryce
    0.55
    Activations Density 0.087%

    No Known Activations