© 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. 2-RES-JB
    11. 9378
    Prev
    Next
    INDEX
    Explanations

    words related to specific parts of the foot (toe and heel)

    oai_token-act-pair · gpt-3.5-turbo

    references to feet, specifically toes and heels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.81
    ioch
    -0.70
    agents
    -0.69
    infeld
    -0.69
     UID
    -0.69
    committee
    -0.68
    interrupted
    -0.67
    edia
    -0.67
    essions
    -0.67
     Nare
    -0.65
    POSITIVE LOGITS
    toe
    1.48
     toe
    1.34
    bridge
    1.03
     toes
    1.01
    bone
    0.90
     heel
    0.85
     nails
    0.83
    weed
    0.82
    wear
    0.79
    bones
    0.78
    Activations Density 0.006%

    No Known Activations