© 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. 4-RES-JB
    11. 15302
    Prev
    Next
    INDEX
    Explanations

    mentions of body parts, specifically legs

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "legs" in various contexts

    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
    NEWS
    -0.71
     retrospective
    -0.71
    vertis
    -0.64
     Tycoon
    -0.64
    urally
    -0.62
    âĸ¬
    -0.62
     Journals
    -0.61
    AMI
    -0.60
    chie
    -0.60
     newsp
    -0.60
    POSITIVE LOGITS
    guards
    0.99
     legs
    0.92
    puter
    0.92
     Legs
    0.90
     amput
    0.87
    bridge
    0.84
    acies
    0.82
    ande
    0.81
    weed
    0.81
    pan
    0.80
    Activations Density 0.011%

    No Known Activations