© 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. 12897
    Prev
    Next
    INDEX
    Explanations

    phrases or statements emphasizing the importance of certain issues

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to significant issues or topics of importance

    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
    lda
    -0.58
    idently
    -0.58
    identally
    -0.57
    ledged
    -0.56
     Barg
    -0.54
     Dunham
    -0.54
    chal
    -0.52
    enment
    -0.52
     Bliss
    -0.51
     Forbidden
    -0.51
    POSITIVE LOGITS
     matter
    0.96
     mattered
    0.83
    matter
    0.80
     matters
    0.72
    RELATED
    0.68
    bleacher
    0.66
     Matter
    0.63
    iframe
    0.61
     shaped
    0.61
    impact
    0.58
    Activations Density 0.019%

    No Known Activations