© 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. 6-RES-JB
    11. 13869
    Prev
    Next
    INDEX
    Explanations

    references to specific exercises or techniques related to squatting

    oai_token-act-pair · gpt-3.5-turbo

    references to specific exercises and their forms within fitness and strength training contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Centauri
    -0.87
    taboola
    -0.77
     Carbuncle
    -0.75
     Sapphire
    -0.75
     Saud
    -0.73
     Pandora
    -0.73
     Aad
    -0.72
    Pand
    -0.71
     UID
    -0.71
     Nay
    -0.69
    POSITIVE LOGITS
     workout
    1.26
     exercises
    1.19
     workouts
    1.18
    ercise
    1.17
     Technique
    1.13
     squats
    1.06
     weights
    0.98
     routine
    0.94
     technique
    0.94
     gymn
    0.93
    Activations Density 0.210%

    No Known Activations