© 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. 3-RES-JB
    11. 15489
    Prev
    Next
    INDEX
    Explanations

    references to submission in a competitive context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to submission techniques in combat sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uld
    -0.75
     Helpful
    -0.71
    Tre
    -0.69
    Newsletter
    -0.69
    minecraft
    -0.68
    iru
    -0.68
    plot
    -0.66
     Transit
    -0.65
    Beer
    -0.65
    arton
    -0.64
    POSITIVE LOGITS
     Showdown
    0.87
     stopp
    0.85
     bouts
    0.84
     rematch
    0.84
     boxer
    0.84
     wrestlers
    0.82
     bout
    0.82
     heavyweight
    0.78
     trainer
    0.77
     fights
    0.77
    Activations Density 0.106%

    No Known Activations