© 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. 5388
    Prev
    Next
    INDEX
    Explanations

    mentions of sports achievements, particularly leading a team to championships or playoffs

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and their achievements

    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
    quickShipAvailable
    -0.85
    uploads
    -0.68
    é¾įå¥ij士
    -0.62
    enery
    -0.62
    shr
    -0.61
     acids
    -0.60
    factor
    -0.60
     exacerbated
    -0.59
    supp
    -0.59
    testing
    -0.58
    POSITIVE LOGITS
     victory
    1.28
     victories
    1.20
     wins
    1.09
     glory
    1.05
     triumph
    0.97
     winning
    0.93
     immortality
    0.93
     championships
    0.92
     redemption
    0.91
     win
    0.90
    Activations Density 0.105%

    No Known Activations