© 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. 10300
    Prev
    Next
    INDEX
    Explanations

    instances of text annotated with certain symbols

    oai_token-act-pair · gpt-3.5-turbo

    dialog or references to significant events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     administr
    -0.93
     ranged
    -0.87
     manifest
    -0.82
     endeav
    -0.80
     arrang
    -0.80
     gest
    -0.79
     organis
    -0.77
     constituted
    -0.76
     incarn
    -0.75
     given
    -0.75
    POSITIVE LOGITS
    Report
    1.16
    Why
    1.09
    WATCH
    1.09
    Advertisements
    1.07
    How
    1.04
    Study
    1.03
    Latest
    1.02
    VIDEO
    1.01
    Woman
    1.01
    Conclusion
    1.01
    Activations Density 0.215%

    No Known Activations