© 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 EvalsExportsAPI 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. 1-RES-JB
    11. 21996
    Prev
    Next
    INDEX
    Explanations

    information related to a specific person named Garnett and Gerrard, potentially emphasizing their performance in sports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific athletes, particularly focusing on Kevin Garnett and Steven Gerrard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Independent
    -0.74
     Mechanical
    -0.67
     geography
    -0.64
     ride
    -0.63
     hrs
    -0.62
     NCT
    -0.62
    ktop
    -0.62
     Tonight
    -0.58
     dispatch
    -0.56
     prevailing
    -0.55
    POSITIVE LOGITS
     Garn
    1.22
     garn
    0.97
    itures
    0.88
    ethyst
    0.88
    spir
    0.87
    ishment
    0.87
    emouth
    0.86
    omore
    0.85
     Pengu
    0.85
    stein
    0.84
    Activations Density 0.010%

    No Known Activations