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. 2-RES-JB
    6. 18012
    Prev
    Next
    INDEX
    Explanations

    keywords related to body parts, specifically focusing on knees

    oai_token-act-pair · gpt-3.5-turbo

    references to the knees and related anatomical features or actions

    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
    Marie
    -0.69
    judicial
    -0.66
    BUG
    -0.65
    hyp
    -0.63
    RY
    -0.63
    vol
    -0.62
    cash
    -0.61
    thumbnails
    -0.60
     departures
    -0.60
    sg
    -0.58
    POSITIVE LOGITS
    mith
    1.31
    creen
    1.22
    paces
    1.21
    pring
    1.18
    ynthesis
    1.17
    pace
    1.17
    hops
    1.16
    erver
    1.10
    cape
    1.09
    peed
    1.05
    Activations Density 0.043%

    No Known Activations