© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 12037
    Prev
    Next
    INDEX
    Explanations

    terms related to legal agreements and licenses

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.63
    âĢİ
    -0.62
    ploy
    -0.62
    naissance
    -0.62
     bureaucracy
    -0.61
     basics
    -0.60
    odynam
    -0.60
     median
    -0.59
    uning
    -0.59
     gard
    -0.59
    POSITIVE LOGITS
     disclaim
    0.95
     WITHOUT
    0.89
     Sponsor
    0.87
     MLG
    0.87
     WARRANT
    0.85
     herein
    0.84
     hereby
    0.82
     Warrant
    0.81
    claimer
    0.81
     Void
    0.80
    Activations Density 0.200%

    No Known Activations