© 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. 3-RES-JB
    11. 8973
    Prev
    Next
    INDEX
    Explanations

    keywords related to the field of biology

    oai_token-act-pair · gpt-3.5-turbo

    references to biology and biologists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arters
    -0.75
    adra
    -0.66
    rail
    -0.65
    Scot
    -0.65
     Territories
    -0.64
     Gallagher
    -0.64
    ammy
    -0.63
    rek
    -0.63
     Mouth
    -0.62
    plings
    -0.62
    POSITIVE LOGITS
     biologist
    1.26
     biologists
    1.20
     biology
    1.18
    biology
    1.06
     Biology
    1.00
     Genetics
    0.99
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.96
    alogy
    0.93
    iology
    0.90
    ynthesis
    0.87
    Activations Density 0.011%

    No Known Activations