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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 564
    Prev
    Next
    INDEX
    Explanations

    dates or time-related words, specifically "today"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "today."

    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
    emaker
    -0.66
    76561
    -0.63
    eer
    -0.62
    chief
    -0.62
    kept
    -0.59
    eers
    -0.59
     Trouble
    -0.58
    coon
    -0.58
    obos
    -0.58
    chest
    -0.57
    POSITIVE LOGITS
     afternoon
    1.19
     morning
    1.09
     evening
    1.00
     marks
    0.77
     flanked
    0.69
    abouts
    0.69
    morning
    0.68
    tical
    0.68
     noon
    0.66
     EDITION
    0.65
    Activations Density 0.049%

    No Known Activations