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. 1-RES-JB
    6. 15328
    Prev
    Next
    INDEX
    Explanations

    news-related words, particularly related to the media outlet "India Today"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the phrase "Today" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.97
     doors
    -0.69
     externalToEVAOnly
    -0.68
    ye
    -0.68
    aine
    -0.66
    igious
    -0.65
    rosse
    -0.65
    ilde
    -0.63
     sudden
    -0.63
     door
    -0.62
    POSITIVE LOGITS
     Today
    1.25
    Today
    1.03
    adays
    0.99
     Tonight
    0.95
     TODAY
    0.90
    today
    0.89
     Yesterday
    0.81
     Tomorrow
    0.79
    Tonight
    0.76
    days
    0.76
    Activations Density 0.008%

    No Known Activations