© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18853
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology and biochemistry, such as DNA, acids, enzymes, and chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    terms related to molecular structures and biological processes

    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
    HUD
    -0.89
    Fest
    -0.81
    soDeliveryDate
    -0.81
    practice
    -0.81
    Weather
    -0.77
     Awareness
    -0.75
     Willie
    -0.74
    pract
    -0.73
     Encounter
    -0.72
    CVE
    -0.72
    POSITIVE LOGITS
     amino
    1.39
     atoms
    1.34
     molecules
    1.32
     nucle
    1.32
     electrons
    1.26
     molecule
    1.22
     phosphate
    1.20
     ions
    1.19
     proteins
    1.18
     electron
    1.13
    Activations Density 0.301%

    No Known Activations