© 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. 8945
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    729
    +0.13
    0.6%
    572
    +0.13
    0.6%
    151
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    748
    +0.13
    0.04
    484
    +0.13
    0.06
    766
    +0.11
    0.06
    Negative Logits
     constitu
    -0.72
     outputs
    -0.70
    ourcing
    -0.68
     audits
    -0.67
     embodiments
    -0.63
     Printed
    -0.62
    æ©Ł
    -0.61
    ibur
    -0.61
    otypes
    -0.61
    olutions
    -0.60
    POSITIVE LOGITS
     his
    0.99
     her
    0.90
    him
    0.81
     wife
    0.80
     daughter
    0.79
     queen
    0.78
     whom
    0.76
    his
    0.75
     His
    0.74
    His
    0.73
    Activations Density 0.435%

    No Known Activations