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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 7793
    Prev
    Next
    INDEX
    Explanations

    terms related to 'foot', such as footnotes, footpath, footprints, and foot soldiers

    oai_token-act-pair · gpt-3.5-turbo

    references to "foot" in various contexts

    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
    acha
    -0.72
    ALD
    -0.70
    eer
    -0.69
    eers
    -0.62
     Learned
    -0.61
     Parenthood
    -0.61
     elig
    -0.59
     elders
    -0.59
     Hodg
    -0.59
    eering
    -0.58
    POSITIVE LOGITS
    notes
    1.27
    bridge
    1.22
    step
    1.18
    steps
    1.18
    prints
    1.15
    falls
    1.14
    path
    1.11
    print
    1.07
    fall
    1.03
    note
    1.02
    Activations Density 0.050%

    No Known Activations