© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23286
    Prev
    Next
    INDEX
    Explanations

    information related to genetics, cell biology, medical treatments, and diseases

    oai_token-act-pair · gpt-3.5-turbo

    discussions around cellular functions and specific types of cells related to disease and medical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Weather
    -0.99
    soDeliveryDate
    -0.99
    aturday
    -0.94
    HUD
    -0.92
    Winter
    -0.82
    iquette
    -0.80
     Surve
    -0.79
    Roll
    -0.78
    wm
    -0.78
     lounge
    -0.77
    POSITIVE LOGITS
     proteins
    1.61
     genes
    1.60
     DNA
    1.54
     genomes
    1.52
     cells
    1.49
     gene
    1.48
     genome
    1.47
     genomic
    1.46
     RNA
    1.46
     mitochond
    1.45
    Activations Density 0.400%

    No Known Activations