© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10706
    Prev
    Next
    INDEX
    Explanations

    numbers related to percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, specifically percentages and numbers associated with age and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gets
    -0.96
    sworth
    -0.86
    lings
    -0.84
    holders
    -0.81
    holder
    -0.79
    folk
    -0.79
    hold
    -0.79
    holding
    -0.72
    âĹ¼
    -0.71
    seeing
    -0.70
    POSITIVE LOGITS
    %:
    0.96
    80
    0.90
     mph
    0.86
    90
    0.83
    ologue
    0.83
    999
    0.81
    ocal
    0.81
    75
    0.81
    644
    0.79
     dB
    0.79
    Activations Density 0.028%

    No Known Activations