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. 0-RES-JB
    6. 23006
    Prev
    Next
    INDEX
    Explanations

    references to body parts, specifically the toes

    oai_token-act-pair · gpt-3.5-turbo

    references to parts of the foot, particularly "toe" and "heel."

    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
    process
    -0.72
     McCorm
    -0.70
     Package
    -0.66
    package
    -0.65
     Sched
    -0.64
    CAP
    -0.63
     Process
    -0.62
    ï
    -0.62
    infeld
    -0.61
    MAS
    -0.61
    POSITIVE LOGITS
     toe
    4.21
    toe
    2.83
     toes
    2.74
     heel
    2.11
     heels
    1.54
     foot
    1.53
     ankle
    1.46
     knee
    1.25
     shoe
    1.24
     tread
    1.24
    Activations Density 0.010%

    No Known Activations