© 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. 11407
    Prev
    Next
    INDEX
    Explanations

    times and locations of sports events or related activities

    oai_token-act-pair · gpt-3.5-turbo

    specific sporting event details, including game times, teams, and locations

    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
     therap
    -0.80
    enegger
    -0.79
     conscientious
    -0.77
     weaving
    -0.75
     corpor
    -0.74
     profession
    -0.73
     professions
    -0.73
     vanity
    -0.71
     welf
    -0.71
     ejac
    -0.70
    POSITIVE LOGITS
     Recap
    1.22
     Playoffs
    1.12
     Highlights
    1.12
    vs
    1.11
     PHI
    1.10
     STATS
    1.08
     vs
    1.06
     Playoff
    1.04
     Bye
    1.03
     Score
    1.01
    Activations Density 0.245%

    No Known Activations