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. 8-RES-JB
    6. 20787
    Prev
    Next
    INDEX
    Explanations

    French and Spanish names, especially involving medical professions or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bender
    -0.61
    ghan
    -0.60
     todd
    -0.59
     Pixar
    -0.58
    wegian
    -0.58
    letcher
    -0.56
    ãģĨ
    -0.56
     FSA
    -0.56
     unc
    -0.56
    ogle
    -0.55
    POSITIVE LOGITS
    bilt
    1.06
    emort
    0.82
    export
    0.76
    tsky
    0.72
    rontal
    0.70
    ctive
    0.65
    sov
    0.64
    oÄŁ
    0.64
    Leaks
    0.64
    rone
    0.63
    Activations Density 0.392%

    No Known Activations