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. 8-RES-JB
    6. 21160
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biology and chemistry, especially focusing on strains, glands, and chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to biological or chemical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ational
    -0.75
    aciously
    -0.70
    itarian
    -0.70
    izen
    -0.68
    ities
    -0.61
    iful
    -0.61
    iser
    -0.57
    orer
    -0.56
     unemploy
    -0.55
    ITY
    -0.54
    POSITIVE LOGITS
    gian
    1.06
    mbol
    1.04
    gdala
    1.04
    cling
    1.03
    outube
    0.98
    tes
    0.95
    lene
    0.94
    tsky
    0.92
    nergy
    0.92
    prus
    0.92
    Activations Density 0.155%

    No Known Activations