© 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. 9-RES-JB
    11. 23236
    Prev
    Next
    INDEX
    Explanations

    gene-related terms and descriptions

    oai_token-act-pair · gpt-3.5-turbo

    specific gene mutations and genetic relationships in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Weather
    -0.88
    Ń·
    -0.82
    ¥µ
    -0.81
    fell
    -0.75
     tents
    -0.75
    taboola
    -0.74
    Street
    -0.74
    ä¸Ĭ
    -0.73
    deb
    -0.73
     sober
    -0.72
    POSITIVE LOGITS
     genes
    1.38
     gene
    1.33
     proteins
    1.28
     mutations
    1.28
     enzyme
    1.25
     mutation
    1.22
     pept
    1.20
     chromosome
    1.20
     mutated
    1.19
     enzymes
    1.16
    Activations Density 0.243%

    No Known Activations