Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 19142
    Prev
    Next
    INDEX
    Explanations

    terms related to physical training, fitness, and health

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical fitness and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onymous
    -0.98
    Gate
    -0.76
     Neighbor
    -0.75
    farious
    -0.74
     veto
    -0.71
    option
    -0.71
    inqu
    -0.70
     bidding
    -0.70
    ulhu
    -0.69
     Shared
    -0.69
    POSITIVE LOGITS
     stamina
    1.52
     workouts
    1.48
     fatigue
    1.43
     muscles
    1.41
     sore
    1.36
     cardio
    1.36
     fatig
    1.34
     muscle
    1.32
     glyc
    1.31
     workout
    1.30
    Activations Density 0.669%

    No Known Activations