© 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. 11-RES-JB
    11. 5599
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific techniques, methods, and research studies

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms related to imaging and analysis techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wont
    -0.73
     perk
    -0.71
    usha
    -0.70
    estate
    -0.70
    deal
    -0.66
    zzy
    -0.63
    grounds
    -0.63
    gency
    -0.63
     Mansion
    -0.63
     loose
    -0.62
    POSITIVE LOGITS
     characterization
    1.39
     analyses
    1.30
     microsc
    1.23
     profiling
    1.22
     imaging
    1.20
     analysis
    1.16
     assay
    1.15
     sequencing
    1.12
    omics
    1.12
     studies
    1.09
    Activations Density 0.208%

    No Known Activations