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. 7377
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific individuals or locations, specifically focusing on the names "Newton" and "Armstrong."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and locations, primarily Newton and Armstrong

    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
    NetMessage
    -0.82
    bour
    -0.82
    pper
    -0.81
    ngth
    -0.81
    hov
    -0.81
    pport
    -0.80
    ques
    -0.78
    ipping
    -0.76
    assic
    -0.76
    DonaldTrump
    -0.74
    POSITIVE LOGITS
    s
    1.07
    ski
    0.93
    sburg
    0.92
    shire
    0.88
    ulators
    0.79
     Revel
    0.77
    ulator
    0.73
    orem
    0.71
    urst
    0.71
     Newton
    0.70
    Activations Density 0.041%

    No Known Activations