© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2427
    Prev
    Next
    INDEX
    Explanations

    words related to jogging

    oai_token-act-pair · gpt-3.5-turbo

    words related to jogging and exercise

    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
     Tale
    -0.83
     ILCS
    -0.74
     negotiators
    -0.73
     careg
    -0.70
     Kul
    -0.67
     spores
    -0.64
     Kubrick
    -0.63
     shatter
    -0.63
     survival
    -0.63
     frag
    -0.63
    POSITIVE LOGITS
    ogged
    1.65
    ogging
    1.62
    sers
    0.86
    ovic
    0.85
    issance
    0.84
    uality
    0.82
    ulator
    0.82
    station
    0.80
    tops
    0.78
    gers
    0.78
    Activations Density 0.013%

    No Known Activations