© 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. 24235
    Prev
    Next
    INDEX
    Explanations

    descriptions related to improved user experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to user experience in various contexts

    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
     filings
    -0.71
    roup
    -0.69
    laws
    -0.66
    haired
    -0.63
    cmp
    -0.63
    nat
    -0.62
    law
    -0.62
    inate
    -0.61
    hom
    -0.61
     grandfather
    -0.61
    POSITIVE LOGITS
    ually
    0.79
     Remastered
    0.79
    Capture
    0.78
    phony
    0.77
    urable
    0.75
    ¥µ
    0.73
     Royale
    0.72
    UAL
    0.72
    earable
    0.72
    iences
    0.70
    Activations Density 0.046%

    No Known Activations