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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4127
    Prev
    Next
    INDEX
    Explanations

    terms related to sports trades, draft picks, and player transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports trades and player exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tests
    -0.83
    Self
    -0.75
     OPER
    -0.74
    YouTube
    -0.72
     eru
    -0.67
    twitch
    -0.67
    UI
    -0.66
    test
    -0.65
     Challenges
    -0.64
     Mothers
    -0.63
    POSITIVE LOGITS
     undrafted
    0.98
     picks
    0.96
     draft
    0.96
     salary
    0.94
     cornerback
    0.92
     prized
    0.91
     waivers
    0.87
     allocation
    0.86
     Picks
    0.85
     defenseman
    0.85
    Activations Density 0.277%

    No Known Activations