© 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. 1-RES-JB
    11. 20533
    Prev
    Next
    INDEX
    Explanations

    references to reports or rapport

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific reports and related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãĥĸ
    -0.72
     Viking
    -0.69
    gling
    -0.63
     Tigers
    -0.63
     Greeks
    -0.62
     slew
    -0.61
     Yankee
    -0.60
     Vikings
    -0.60
     Gothic
    -0.59
     Egyptians
    -0.59
    POSITIVE LOGITS
     Rapp
    1.40
    eur
    0.90
    irtual
    0.90
    ett
    0.87
    etz
    0.86
    aste
    0.85
    ort
    0.83
    eport
    0.82
     newsp
    0.80
    eworthy
    0.80
    Activations Density 0.009%

    No Known Activations