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. 19110
    Prev
    Next
    INDEX
    Explanations

    names of nationalities or cultures

    oai_token-act-pair · gpt-3.5-turbo

    names of various cuisines or types of food

    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
    odder
    -0.96
    ueller
    -0.75
    ertodd
    -0.75
    ividual
    -0.74
    perty
    -0.71
    lease
    -0.71
    abilities
    -0.70
    olicy
    -0.69
    vable
    -0.69
    isconsin
    -0.68
    POSITIVE LOGITS
     immigrant
    1.07
     immigrants
    1.06
     ancestry
    1.02
     heritage
    0.96
    oslov
    0.92
     proverb
    0.92
     descent
    0.90
     cuisine
    0.90
    istani
    0.89
    apolis
    0.83
    Activations Density 0.153%

    No Known Activations