© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 13398
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to kidney-related medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to kidney health 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
     Stars
    -0.76
     Corsair
    -0.75
     Guides
    -0.70
    Stars
    -0.70
    ships
    -0.69
    antz
    -0.69
     Fant
    -0.69
    ét
    -0.69
    Drag
    -0.69
     Tempest
    -0.68
    POSITIVE LOGITS
     kidney
    3.71
     kidneys
    2.72
     renal
    2.45
     urinary
    1.44
     urine
    1.44
     liver
    1.41
     bladder
    1.38
     cardiac
    1.31
     prostate
    1.31
     leukemia
    1.21
    Activations Density 0.023%

    No Known Activations