© 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. 0-RES-JB
    11. 9919
    Prev
    Next
    INDEX
    Explanations

    references to leisure activities or time spent for recreational purposes

    oai_token-act-pair · gpt-3.5-turbo

    references to leisure activities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OG
    -0.73
    Jam
    -0.69
    DNA
    -0.66
    reb
    -0.66
    va
    -0.66
    cko
    -0.64
    Known
    -0.63
     strings
    -0.63
    ORY
    -0.62
    ems
    -0.62
    POSITIVE LOGITS
     leisure
    4.09
    isure
    2.21
     amuse
    1.16
     recreation
    1.15
     amusement
    1.10
     lux
    1.02
     pleasure
    1.02
     frivol
    1.01
     brisk
    0.98
     relaxing
    0.97
    Activations Density 0.033%

    No Known Activations