© 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. 12790
    Prev
    Next
    INDEX
    Explanations

    statements related to opinions on controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    content related to health concerns and policies regarding substances like marijuana

    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
    luster
    -0.66
     Plot
    -0.61
     sqor
    -0.61
     Ful
    -0.60
    fortune
    -0.58
     Booth
    -0.58
     Roc
    -0.57
    stakes
    -0.55
     Together
    -0.55
     Sack
    -0.54
    POSITIVE LOGITS
     exemptions
    0.93
     regulated
    0.87
     lawfully
    0.86
     exempted
    0.86
     complying
    0.86
     compliance
    0.84
     legisl
    0.84
     abiding
    0.82
     exemption
    0.78
     enforcing
    0.78
    Activations Density 0.753%

    No Known Activations