Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 20409
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, specifically focused on liver-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to liver health and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Occupations
    -0.75
     Strategic
    -0.74
     Emerging
    -0.68
     Fif
    -0.68
     Religious
    -0.67
     Psychological
    -0.67
     Grad
    -0.66
     Nich
    -0.65
     Pathfinder
    -0.64
     Prayer
    -0.64
    POSITIVE LOGITS
     liver
    1.25
    itionally
    0.97
     kidneys
    0.95
     transplant
    0.93
    ivery
    0.88
     transpl
    0.86
     marrow
    0.83
     hep
    0.82
     enzymes
    0.81
     kidney
    0.81
    Activations Density 0.006%

    No Known Activations