© 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. 6585
    Prev
    Next
    INDEX
    Explanations

    materials and characteristics related to durable and protective design in products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to materials and their properties

    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
    cffffcc
    -0.85
    ithmetic
    -0.77
    OPA
    -0.71
    minent
    -0.70
    ilater
    -0.69
    iddles
    -0.69
    minute
    -0.68
    irez
    -0.68
    aughter
    -0.68
    ;;;;;;;;;;;;
    -0.66
    POSITIVE LOGITS
     coating
    1.42
     polymer
    1.37
     adhesive
    1.33
     membrane
    1.31
     insulation
    1.31
     latex
    1.30
     resin
    1.29
     foam
    1.29
     fabrics
    1.25
     coated
    1.25
    Activations Density 0.237%

    No Known Activations