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. 10962
    Prev
    Next
    INDEX
    Explanations

    words related to physical medical conditions focused on neurological and muscular health, specifically terms ending in 'phy'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical conditions and diseases

    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
     wait
    -0.62
     Angels
    -0.61
     waiting
    -0.60
     elves
    -0.59
     batch
    -0.58
     expecting
    -0.58
     anticipating
    -0.58
     Express
    -0.58
     Ask
    -0.58
     ans
    -0.58
    POSITIVE LOGITS
    phy
    4.96
    phia
    1.75
    pha
    1.52
    phys
    1.30
    phies
    1.22
    phe
    1.15
    ph
    1.07
    phis
    1.07
    cious
    1.06
    opy
    1.05
    Activations Density 0.003%

    No Known Activations