© 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. 32654
    Prev
    Next
    INDEX
    Explanations

    references to authority figures or leaders in various contexts

    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
    679
    +0.14
    0.6%
    133
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.02
    679
    +0.10
    0.02
    698
    +0.10
    0.02
    Negative Logits
     Scotia
    -0.95
     Pwr
    -0.85
     CTR
    -0.75
     Verge
    -0.69
     Trails
    -0.65
    ctica
    -0.64
    selves
    -0.64
     Coch
    -0.63
    lease
    -0.62
     Lauder
    -0.61
    POSITIVE LOGITS
    hips
    1.00
    es
    0.91
    fights
    0.87
    anova
    0.85
    ery
    0.84
    enstein
    0.81
    fight
    0.81
    force
    0.80
    nut
    0.79
    nuts
    0.77
    Activations Density 0.107%

    No Known Activations