© 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. 12117
    Prev
    Next
    INDEX
    Explanations

    sentences related to sports events

    oai_token-act-pair · gpt-3.5-turbo

    instances of sports-related actions involving scoring or attempts to score

    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
     behaviours
    -0.77
    lihood
    -0.76
    ggle
    -0.67
     consultation
    -0.67
    beh
    -0.67
    hap
    -0.66
     enqu
    -0.66
     exams
    -0.66
     learnt
    -0.65
    wordpress
    -0.65
    POSITIVE LOGITS
     Santana
    0.79
     PHI
    0.79
     Whitney
    0.78
     linem
    0.78
     Elias
    0.78
     pinch
    0.78
     Jarrett
    0.78
     RBI
    0.78
     Ricardo
    0.77
     Devin
    0.76
    Activations Density 0.102%

    No Known Activations