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. 10-RES-JB
    6. 11847
    Prev
    Next
    INDEX
    Explanations

    exercises and movements related to fitness and strength training, particularly focusing on squat-related activities

    oai_token-act-pair · gpt-3.5-turbo

    guidance and instructions related to exercise techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Minecraft
    -0.90
     Turing
    -0.85
     Forensic
    -0.79
     Virus
    -0.76
     Aad
    -0.74
     apocalyptic
    -0.74
     Sapphire
    -0.74
    Pand
    -0.73
    avorite
    -0.72
     anonymous
    -0.72
    POSITIVE LOGITS
     muscles
    1.42
     hips
    1.32
     posture
    1.31
     squats
    1.28
     thighs
    1.26
     knees
    1.26
     abdom
    1.23
     pelvic
    1.22
     flex
    1.17
     exercises
    1.16
    Activations Density 0.233%

    No Known Activations