Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10600
    Prev
    Next
    INDEX
    Explanations

    genes or genetic-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to genetic concepts and terminology

    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
    rame
    -0.81
     Fired
    -0.80
    boarding
    -0.74
     Pastebin
    -0.73
    staff
    -0.73
    board
    -0.71
     Cancel
    -0.70
    mins
    -0.70
    bus
    -0.69
     Tracker
    -0.68
    POSITIVE LOGITS
     genetic
    3.50
     genetics
    3.02
     Genetic
    2.67
     Genetics
    2.38
     genetically
    2.31
     genomic
    2.17
     genes
    2.16
     genome
    2.11
     gene
    2.03
     DNA
    1.88
    Activations Density 0.018%

    No Known Activations