© 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. 10-RES-JB
    11. 13907
    Prev
    Next
    INDEX
    Explanations

    terms related to proteins and their role in biological processes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of protein and its various contexts in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ragon
    -0.73
    rek
    -0.71
    orld
    -0.69
     Rebels
    -0.68
    quished
    -0.66
    76561
    -0.66
    een
    -0.66
     Moff
    -0.64
    essee
    -0.64
    GAME
    -0.63
    POSITIVE LOGITS
    aceous
    1.35
     synthesis
    1.09
     isolate
    1.02
    protein
    0.97
     proteins
    0.95
     protein
    0.94
    amide
    0.92
     phosph
    0.92
     phosphate
    0.92
     amino
    0.92
    Activations Density 0.038%

    No Known Activations