© 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. 0-RES-JB
    11. 10379
    Prev
    Next
    INDEX
    Explanations

    references to DNA

    oai_token-act-pair · gpt-3.5-turbo

    mentions of DNA and its related concepts

    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
     stopp
    -0.73
    ares
    -0.72
    ................
    -0.71
    ........
    -0.69
    ,-
    -0.68
    ominated
    -0.67
    moderate
    -0.66
    Steam
    -0.66
    chant
    -0.65
     warr
    -0.65
    POSITIVE LOGITS
     DNA
    3.92
    DNA
    3.11
     genome
    1.85
     genetic
    1.77
     genomic
    1.76
     RNA
    1.75
     genomes
    1.74
     genes
    1.71
     chromosomes
    1.68
     chromosome
    1.64
    Activations Density 0.024%

    No Known Activations