Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7819
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical fitness and weightlifting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical fitness and athletic performance

    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
     Nab
    -0.66
    named
    -0.66
    bek
    -0.66
     Beware
    -0.66
     Crimes
    -0.66
    said
    -0.64
     Romeo
    -0.63
     Say
    -0.63
     Messenger
    -0.62
     UID
    -0.62
    POSITIVE LOGITS
     physique
    1.07
     athletes
    1.02
    userc
    0.99
     fatig
    0.96
     regimen
    0.96
     endurance
    0.95
    ercise
    0.92
     athlete
    0.92
     workout
    0.91
     gym
    0.90
    Activations Density 0.345%

    No Known Activations