© 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. 8764
    Prev
    Next
    INDEX
    Explanations

    instances of questioning or challenges regarding authority and social norms

    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
    644
    +0.09
    0.4%
    54
    +0.09
    0.4%
    86
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.11
    143
    +0.09
    0.09
    292
    +0.09
    0.06
    Negative Logits
    pict
    -0.70
    onto
    -0.65
    izational
    -0.64
    chieve
    -0.64
    ellow
    -0.61
     glyph
    -0.60
    lore
    -0.59
    enture
    -0.58
     celebr
    -0.56
    company
    -0.55
    POSITIVE LOGITS
    Answer
    1.59
     Answer
    1.17
     answer
    0.93
     answered
    0.91
     answers
    0.84
    Well
    0.81
     Nope
    0.80
    Absolutely
    0.78
    RH
    0.76
     Well
    0.75
    Activations Density 0.530%

    No Known Activations