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. 6-RES-JB
    6. 4636
    Prev
    Next
    INDEX
    Explanations

    terms related to liver health and liver-related topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the liver and its related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minus
    -0.78
    é¾įå¥ij士
    -0.76
     Wildcats
    -0.74
    ãģ®éŃĶ
    -0.68
    ãĤ®
    -0.67
     Fif
    -0.65
    Rated
    -0.63
     Occupations
    -0.63
     Subtle
    -0.63
     Strategic
    -0.62
    POSITIVE LOGITS
     liver
    1.05
     cir
    1.05
     transplant
    0.92
     detox
    0.90
     enzymes
    0.89
     marrow
    0.84
     glyc
    0.82
     gland
    0.82
     enzyme
    0.82
     transpl
    0.79
    Activations Density 0.018%

    No Known Activations