© 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. 11400
    Prev
    Next
    INDEX
    Explanations

    instances of scores or points in sports games

    oai_token-act-pair · gpt-3.5-turbo

    phrases or references related to game scores and outcomes

    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
    issance
    -0.67
    catentry
    -0.63
    itte
    -0.63
    eters
    -0.63
    channelAvailability
    -0.62
    hai
    -0.60
    Values
    -0.60
    /(
    -0.59
     guiIcon
    -0.59
     UNCLASSIFIED
    -0.58
    POSITIVE LOGITS
     overtime
    1.15
     stopp
    0.98
     front
    0.89
     regulation
    0.89
     OT
    0.87
     Game
    0.86
     spite
    0.85
    ked
    0.84
    bound
    0.82
     Week
    0.81
    Activations Density 0.099%

    No Known Activations