© 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. 24327
    Prev
    Next
    INDEX
    Explanations

    references to swimming activities

    oai_token-act-pair · gpt-3.5-turbo

    references to swimming and related activities

    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
     crushing
    -0.71
    oppers
    -0.70
    relevant
    -0.70
     paving
    -0.65
    ________________________
    -0.62
    oned
    -0.61
    aples
    -0.60
     setback
    -0.60
    ################
    -0.59
     crush
    -0.59
    POSITIVE LOGITS
     Swim
    1.42
     swim
    1.28
    suit
    1.00
    suits
    1.00
    boats
    0.95
    boat
    0.94
    tub
    0.89
     swimming
    0.83
     fins
    0.82
    halla
    0.82
    Activations Density 0.004%

    No Known Activations