Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 237
    Prev
    Next
    INDEX
    Explanations

    terms related to weight classes and events in combat sports

    oai_token-act-pair · gpt-4-turbo

    phrases related to weight, especially in the context of sports and competitions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with competitive fighting and weight classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uld
    -0.77
    SPONSORED
    -0.71
    iru
    -0.68
    minecraft
    -0.67
    ascal
    -0.66
    sels
    -0.63
    government
    -0.63
    ishops
    -0.63
    brew
    -0.63
    installed
    -0.62
    POSITIVE LOGITS
     Showdown
    0.87
     rematch
    0.86
     bouts
    0.85
     bout
    0.83
     stopp
    0.81
     prim
    0.79
     wrestlers
    0.79
     championship
    0.77
     Championship
    0.76
     boxer
    0.76
    Activations Density 0.182%

    No Known Activations