© 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. 26513
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "honest" and related terms describing integrity and trustworthiness

    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
    710
    +0.13
    0.6%
    526
    +0.09
    0.4%
    88
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.13
    0.03
    762
    +0.09
    0.04
    96
    +0.09
    0.03
    Negative Logits
    rior
    -0.82
     Warrant
    -0.70
    İĭ
    -0.69
     curfew
    -0.69
     GEAR
    -0.67
     Supplement
    -0.66
     Krish
    -0.66
    uled
    -0.66
    riors
    -0.64
    oval
    -0.63
    POSITIVE LOGITS
     broker
    0.89
     mistake
    0.83
     mistakes
    0.81
     appraisal
    0.80
     honest
    0.80
    spection
    0.72
     truthful
    0.71
     brokers
    0.70
    enstein
    0.69
     seekers
    0.69
    Activations Density 0.455%

    No Known Activations