© 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. 0-RES-JB
    11. 5059
    Prev
    Next
    INDEX
    Explanations

    terms related to muscle function and physiology

    oai_token-act-pair · gpt-3.5-turbo

    words relating to muscles and muscular activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Collector
    -0.82
     Cake
    -0.71
    christ
    -0.69
    mitting
    -0.68
    imer
    -0.67
     Dahl
    -0.66
    onymous
    -0.66
     Happ
    -0.66
    rant
    -0.66
    child
    -0.66
    POSITIVE LOGITS
     muscles
    3.58
     muscle
    2.86
     Muscle
    2.05
     muscular
    1.91
     tendon
    1.55
    iceps
    1.44
     physique
    1.39
     skeletal
    1.35
     posture
    1.28
     abdom
    1.24
    Activations Density 0.031%

    No Known Activations