© 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 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. 385
    Prev
    Next
    INDEX
    Explanations

    the word "genetic"

    oai_token-act-pair · gpt-4-turbo

    phrases related to genetic information and markers

    oai_token-act-pair · gpt-3.5-turbo

    references to genetics and genetic-related concepts

    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
    yers
    -0.86
    alach
    -0.80
    amina
    -0.77
     Springs
    -0.71
    pherd
    -0.70
    lain
    -0.70
    shire
    -0.70
    rentice
    -0.69
     Christy
    -0.68
    swer
    -0.68
    POSITIVE LOGITS
     genetic
    1.01
     predis
    1.00
    etically
    0.98
    alogy
    0.96
     ancestry
    0.94
     mutation
    0.93
     biologist
    0.93
     genetics
    0.91
     destiny
    0.88
     recomb
    0.85
    Activations Density 0.011%

    No Known Activations