© 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. 12-RES-JB
    11. 2958
    Prev
    Next
    INDEX
    Explanations

    phrases related to fantasy sports and specific fantasy sports terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms and references related to fantasy sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Debor
    -0.73
    irez
    -0.72
     spaced
    -0.67
     Tanz
    -0.64
    ermanent
    -0.63
    interstitial
    -0.62
    demon
    -0.60
     declass
    -0.60
     Aden
    -0.59
    duration
    -0.59
    POSITIVE LOGITS
     football
    1.10
    football
    1.07
     Football
    1.07
    land
    0.87
    Football
    0.86
     baseball
    0.84
    Pros
    0.84
     Baseball
    0.80
     Flight
    0.77
    basketball
    0.76
    Activations Density 0.038%

    No Known Activations