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. 4-RES-JB
    6. 17828
    Prev
    Next
    INDEX
    Explanations

    words related to human legs

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries or situations involving legs

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

    No Comments

    Negative Logits
    aukee
    -0.71
    hower
    -0.65
    jri
    -0.63
    ongyang
    -0.63
     vacancy
    -0.61
    tery
    -0.61
    ettings
    -0.61
     Tycoon
    -0.61
    cffff
    -0.60
     groundwater
    -0.58
    POSITIVE LOGITS
    acies
    1.12
    iev
    0.90
    isl
    0.89
    chair
    0.87
    locks
    0.86
    itimate
    0.85
     leg
    0.85
    cop
    0.81
     Leg
    0.80
     amput
    0.80
    Activations Density 0.008%

    No Known Activations