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. 9-RES-JB
    6. 16812
    Prev
    Next
    INDEX
    Explanations

    words related to physical fitness and exercise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fitness and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unciation
    -0.78
    pard
    -0.72
    akedown
    -0.72
    unci
    -0.71
    agall
    -0.70
    enthal
    -0.67
    amn
    -0.67
    afort
    -0.66
    opsis
    -0.66
    asta
    -0.64
    POSITIVE LOGITS
     Trainer
    1.06
     trainer
    1.02
     trainers
    0.95
     regimen
    0.94
     fitness
    0.89
    letes
    0.87
    wear
    0.81
     promot
    0.81
     physique
    0.79
     athletes
    0.78
    Activations Density 0.071%

    No Known Activations