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. 0-RES-JB
    6. 23838
    Prev
    Next
    INDEX
    Explanations

    phrases related to anatomical regions, specifically the upper part of the body

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms that refer to "upper" sections or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Netflix
    -0.70
    advertising
    -0.69
    ba
    -0.65
     Cyborg
    -0.64
    Fund
    -0.64
    rea
    -0.63
    rent
    -0.63
    flix
    -0.63
    arium
    -0.63
    lic
    -0.62
    POSITIVE LOGITS
     upper
    3.64
    upper
    2.50
     Upper
    2.43
     lower
    1.82
    Lower
    1.74
    lower
    1.68
     Lower
    1.67
     outer
    1.33
     upward
    1.21
     inner
    1.19
    Activations Density 0.009%

    No Known Activations