© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 22973
    Prev
    Next
    INDEX
    Explanations

    dates or time-related keywords

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "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
    -0.86
    este
    -0.72
     mustard
    -0.68
     doors
    -0.68
    alcohol
    -0.68
     tongues
    -0.67
     heav
    -0.67
    emaker
    -0.66
     kindred
    -0.64
     wells
    -0.63
    POSITIVE LOGITS
    Today
    1.16
     Today
    1.11
    adays
    1.00
     Tonight
    0.97
    Tonight
    0.93
    Yesterday
    0.90
    today
    0.90
     Yesterday
    0.84
     afternoon
    0.84
     TODAY
    0.81
    Activations Density 0.013%

    No Known Activations