© 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. 11380
    Prev
    Next
    INDEX
    Explanations

    words related to molecular biology, especially focusing on nucleotides and promoters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to molecular biology, specifically focusing on cell components and biological processes

    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
     Daylight
    -0.81
    Access
    -0.80
    bucks
    -0.77
    heed
    -0.75
     CoC
    -0.74
    ampunk
    -0.72
     Canterbury
    -0.72
    asters
    -0.72
     Gears
    -0.72
    crafted
    -0.71
    POSITIVE LOGITS
     nucleus
    3.61
     nucle
    2.18
     promoter
    1.73
    ucle
    1.50
     promoters
    1.49
     embryo
    1.34
     mitochond
    1.31
     germ
    1.28
     hypothal
    1.23
     hippocampus
    1.18
    Activations Density 0.065%

    No Known Activations