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. 10-RES-JB
    6. 7322
    Prev
    Next
    INDEX
    Explanations

    words related to tuberculosis

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "Tu" and its variations, likely indicating a specific focus on tuberculosis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SPD
    -0.70
    rings
    -0.67
     constants
    -0.58
     streng
    -0.57
    washing
    -0.57
     angels
    -0.57
     indications
    -0.57
     respecting
    -0.57
     Colossus
    -0.56
     attracting
    -0.55
    POSITIVE LOGITS
    fts
    1.42
    pper
    1.19
    ition
    1.14
    kson
    1.12
    fty
    1.11
    ples
    1.09
    cci
    1.06
    Tu
    1.05
    isine
    1.04
    culosis
    1.03
    Activations Density 0.021%

    No Known Activations