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

    Neuronpedia

    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. 2-RES-JB
    11. 19049
    Prev
    Next
    INDEX
    Explanations

    statements related to genetic material, specifically chromosome numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific chromosomes and genetic terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icka
    -0.94
    erva
    -0.94
    ornia
    -0.92
    ¥µ
    -0.87
     sqor
    -0.82
    £ı
    -0.80
    ofi
    -0.80
    recated
    -0.80
    acious
    -0.79
    abit
    -0.79
    POSITIVE LOGITS
     chromosomes
    1.01
     hapl
    0.91
     chromosome
    0.86
     DNA
    0.85
    ãĥīãĥ©ãĤ´ãĥ³
    0.79
     Siber
    0.76
     Genetic
    0.76
     bottleneck
    0.74
     abnormalities
    0.73
     Trigger
    0.73
    Activations Density 0.020%

    No Known Activations