© 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. 11-RES-JB
    11. 12863
    Prev
    Next
    INDEX
    Explanations

    numbers related to percentages and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to percentages and monetary values

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    kid
    -0.64
     suffice
    -0.63
     Lack
    -0.61
    dale
    -0.58
    glas
    -0.58
    encrypted
    -0.58
    rera
    -0.57
    inas
    -0.56
    ngth
    -0.56
     reformed
    -0.56
    POSITIVE LOGITS
    fold
    1.16
    %.
    1.11
    %,
    1.10
     percent
    1.06
    %;
    1.03
     percentage
    1.02
    %:
    1.01
     basis
    0.98
     points
    0.96
    percent
    0.95
    Activations Density 0.111%

    No Known Activations