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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19876
    Prev
    Next
    INDEX
    Explanations

    genes or genetic information

    oai_token-act-pair · gpt-3.5-turbo

    references to specific genes and genetic conditions

    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
    ooters
    -0.82
    ä¸Ĭ
    -0.81
    tops
    -0.71
     Loaded
    -0.70
    planes
    -0.70
    boards
    -0.70
    staff
    -0.69
    oons
    -0.69
    ppa
    -0.68
    aturdays
    -0.68
    POSITIVE LOGITS
     gene
    3.60
     genes
    2.01
     Gene
    1.97
     genome
    1.89
     allele
    1.86
     genetic
    1.84
    Gene
    1.82
     chromosome
    1.63
     enzyme
    1.54
     Genetic
    1.51
    Activations Density 0.018%

    No Known Activations