Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 4226
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and medications

    oai_token-act-pair · gpt-3.5-turbo

    chemical substances and their interactions

    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
    å£
    -0.79
     Gunn
    -0.78
    FontSize
    -0.71
    anooga
    -0.68
    ģĸ
    -0.68
    soDeliveryDate
    -0.67
    ĩ
    -0.67
    å·
    -0.67
    orio
    -0.67
    REC
    -0.66
    POSITIVE LOGITS
    amide
    1.31
     phosphate
    1.26
     sulf
    1.22
     acet
    1.17
     chloride
    1.16
     oxide
    1.16
     capsules
    1.15
     supplementation
    1.14
     inhibitors
    1.14
     sulph
    1.14
    Activations Density 0.153%

    No Known Activations