© 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. 12905
    Prev
    Next
    INDEX
    Explanations

    statistics about various numerical rankings or rates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the highest statistical rates or levels of various phenomena

    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
    ateurs
    -0.87
    ionics
    -0.75
    enda
    -0.74
    PAC
    -0.72
    hend
    -0.71
    nothing
    -0.70
    ĪĴ
    -0.70
    assetsadobe
    -0.69
    olph
    -0.68
    ģĸ
    -0.68
    POSITIVE LOGITS
     number
    1.70
     incidence
    1.68
     prevalence
    1.66
     percentage
    1.62
     rate
    1.60
     proportion
    1.54
     ratio
    1.39
     amount
    1.33
     population
    1.29
     numbers
    1.23
    Activations Density 0.242%

    No Known Activations