© 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. 10-RES-JB
    11. 18719
    Prev
    Next
    INDEX
    Explanations

    references to DNA and genetic testing

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osw
    -0.86
    rir
    -0.80
    cffffcc
    -0.77
    owered
    -0.77
    ments
    -0.73
    olicy
    -0.72
    nos
    -0.72
    pheus
    -0.70
    neapolis
    -0.69
    izo
    -0.69
    POSITIVE LOGITS
     molecule
    1.13
     sequencing
    1.04
     methyl
    1.04
     synthesis
    1.02
     strand
    1.02
     molecules
    1.00
     polymer
    1.00
     strands
    1.00
     fragments
    0.97
     hapl
    0.97
    Activations Density 0.032%

    No Known Activations