© 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. 12-RES-JB
    11. 3083
    Prev
    Next
    INDEX
    Explanations

    genetic and ancestry-related terms/terms associated with DNA analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to DNA and genetic analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ment
    -0.70
    ments
    -0.69
    erent
    -0.64
    person
    -0.64
    ocrat
    -0.63
    pheus
    -0.63
     Osw
    -0.61
    lando
    -0.61
    horn
    -0.60
    cffffcc
    -0.60
    POSITIVE LOGITS
     methyl
    1.04
     sequences
    0.97
     sequencing
    0.95
    alogy
    0.92
     extracted
    0.92
     strand
    0.92
     polymer
    0.91
     strands
    0.89
     replication
    0.88
     sequence
    0.87
    Activations Density 0.080%

    No Known Activations