© 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. 3302
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating movement or progression in sports contexts

    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
     Situation
    -0.65
    essa
    -0.63
    advertisement
    -0.63
    creen
    -0.63
     calendars
    -0.61
    ________________
    -0.59
     anomalies
    -0.59
     surroundings
    -0.58
    eties
    -0.58
     abusers
    -0.57
    POSITIVE LOGITS
     undrafted
    1.03
     undefeated
    0.98
     unbeaten
    0.95
     toe
    0.86
    lems
    0.81
     bowling
    0.78
     0
    0.75
    istle
    0.75
     è£ıè¦ļéĨĴ
    0.73
    yne
    0.73
    Activations Density 0.049%

    No Known Activations