© 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. 7-RES-JB
    11. 14250
    Prev
    Next
    INDEX
    Explanations

    names of people and their professions

    oai_token-act-pair · gpt-3.5-turbo

    names of professionals and their roles

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Attach
    -0.58
    LESS
    -0.55
    Again
    -0.50
    Sov
    -0.49
     unbeliev
    -0.49
     meas
    -0.48
    wcs
    -0.48
    *.
    -0.47
     fruition
    -0.47
    VALUE
    -0.47
    POSITIVE LOGITS
     LL
    0.60
     Swansea
    0.58
     Managing
    0.57
    director
    0.56
     Architects
    0.56
    buquerque
    0.53
     Judicial
    0.53
     councillor
    0.53
     pastor
    0.53
     chairman
    0.53
    Activations Density 0.398%

    No Known Activations