© 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. 30810
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making decisions

    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
    706
    +0.10
    0.4%
    364
    +0.10
    0.4%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.10
    0.07
    611
    +0.10
    0.07
    242
    +0.09
    0.06
    Negative Logits
    76561
    -0.89
    lessly
    -0.75
    atum
    -0.72
    atis
    -0.70
    atically
    -0.68
    uko
    -0.67
    azo
    -0.65
     Compensation
    -0.65
    uated
    -0.65
    REDACTED
    -0.64
    POSITIVE LOGITS
    arching
    0.75
    sharp
    0.68
     shape
    0.66
    NAS
    0.64
     helm
    0.63
     cues
    0.62
     innovate
    0.60
     stock
    0.59
     reins
    0.59
    Ħ¢
    0.59
    Activations Density 0.445%

    No Known Activations