© 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. 11-RES-JB
    11. 5308
    Prev
    Next
    INDEX
    Explanations

    mentions of sports trades and player acquisitions

    oai_token-act-pair · gpt-3.5-turbo

    references to player trades and draft picks in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Challenges
    -0.80
     Mothers
    -0.76
    enges
    -0.71
    sth
    -0.71
     associations
    -0.70
    onduct
    -0.66
    emet
    -0.66
     Kappa
    -0.66
    agame
    -0.65
     Modes
    -0.65
    POSITIVE LOGITS
     pricey
    0.99
     assets
    0.97
     prized
    0.92
     veteran
    0.91
     conditional
    0.91
     unprotected
    0.89
     asset
    0.89
     cheaper
    0.86
     acquisition
    0.86
     defenseman
    0.85
    Activations Density 0.235%

    No Known Activations