© 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. 0-RES-JB
    11. 15582
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the sports industry, particularly Major League Baseball

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Major"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creations
    -0.76
     exch
    -0.73
    aic
    -0.66
     absor
    -0.64
    ĺħ
    -0.64
    vine
    -0.63
     rack
    -0.63
     unprotected
    -0.62
     vacuum
    -0.62
    =""
    -0.62
    POSITIVE LOGITS
     Major
    3.83
    Major
    2.70
     Minor
    2.28
    major
    1.96
     Maj
    1.72
    Minor
    1.68
     major
    1.51
     majors
    1.46
     minor
    1.38
     Corpor
    1.35
    Activations Density 0.011%

    No Known Activations