© 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. 7-RES-JB
    11. 2101
    Prev
    Next
    INDEX
    Explanations

    terms related to exercise and physical fitness, particularly focusing on squats

    oai_token-act-pair · gpt-3.5-turbo

    references to squat techniques and exercises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.81
     Moj
    -0.80
     Centauri
    -0.77
     Bahá
    -0.76
     Orwell
    -0.75
    Pand
    -0.75
     Pandora
    -0.74
     Noir
    -0.74
     Paran
    -0.73
     Carbuncle
    -0.73
    POSITIVE LOGITS
     workout
    1.35
     workouts
    1.27
     exercises
    1.22
     Technique
    1.22
    ercise
    1.15
     physique
    1.13
     squats
    1.11
     muscles
    1.09
     weights
    1.02
     gym
    1.02
    Activations Density 0.266%

    No Known Activations