© 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. 26312
    Prev
    Next
    INDEX
    Explanations

    terms related to overriding functions or behaviors in programming contexts

    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
    220
    +0.10
    0.4%
    379
    +0.10
    0.4%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.04
    326
    +0.10
    0.04
    3
    +0.09
    0.02
    Negative Logits
    istics
    -0.84
     Drum
    -0.74
    Haunted
    -0.71
     Jackets
    -0.70
    =-=-=-=-=-=-=-=-
    -0.68
     Gael
    -0.68
    ivism
    -0.67
    STON
    -0.67
    pring
    -0.66
     Bullets
    -0.65
    POSITIVE LOGITS
    idden
    0.99
    ptions
    0.82
    vention
    0.77
    uled
    0.76
    ibly
    0.72
    ride
    0.69
    ingly
    0.69
    uling
    0.68
     override
    0.68
     warnings
    0.67
    Activations Density 0.283%

    No Known Activations