© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16777
    Prev
    Next
    INDEX
    Explanations

    references to physical exercises and workout activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exercise and workouts

    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
     Dahl
    -0.95
    asp
    -0.74
    ingu
    -0.70
     Orb
    -0.68
    DF
    -0.68
     Edmund
    -0.67
     Lily
    -0.65
     Serpent
    -0.65
     flags
    -0.64
    aji
    -0.63
    POSITIVE LOGITS
     workout
    3.00
     workouts
    2.73
     trainer
    1.36
     gym
    1.34
    abolic
    1.26
     booster
    1.15
     regimen
    1.14
     lockout
    1.14
     cardio
    1.11
     treadmill
    1.09
    Activations Density 0.019%

    No Known Activations