© 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. 9-RES-JB
    11. 24284
    Prev
    Next
    INDEX
    Explanations

    descriptions of items or products

    oai_token-act-pair · gpt-3.5-turbo

    elements related to nurturing and care

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     egreg
    -0.95
     DOJ
    -0.86
     squarely
    -0.85
     unilaterally
    -0.84
     obfusc
    -0.79
    termination
    -0.79
     downgrade
    -0.79
     contingency
    -0.78
     jurisd
    -0.76
     bottleneck
    -0.75
    POSITIVE LOGITS
     festive
    1.00
    yrics
    0.99
     decoration
    0.98
     Gifts
    0.93
     Happiness
    0.92
     poems
    0.90
     compliments
    0.90
     Wonderful
    0.89
     amuse
    0.89
     playful
    0.89
    Activations Density 1.177%

    No Known Activations