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. 8-RES-JB
    6. 16391
    Prev
    Next
    INDEX
    Explanations

    phrases related to the squat exercise and its various aspects such as technique, depth, mechanics, efficiency, and accessories

    oai_token-act-pair · gpt-3.5-turbo

    content related to squats and strength training

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Noir
    -0.85
    Pand
    -0.79
     Kafka
    -0.76
     Pandora
    -0.76
    ocument
    -0.75
    angered
    -0.71
     Crimes
    -0.70
    chard
    -0.69
     Joyce
    -0.68
     Rarity
    -0.67
    POSITIVE LOGITS
     workout
    1.42
     workouts
    1.34
     physique
    1.20
     regimen
    1.11
     exercises
    1.09
     athletes
    1.07
     creatine
    1.06
     gym
    1.05
     athlet
    1.04
    abolic
    1.03
    Activations Density 0.173%

    No Known Activations