© 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. 0-RES-JB
    11. 8272
    Prev
    Next
    INDEX
    Explanations

    current events or activities happening on a specific day

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bodily
    -0.68
    oi
    -0.61
     arms
    -0.60
    azard
    -0.57
     antagonist
    -0.57
     alternate
    -0.57
     asses
    -0.56
     possibly
    -0.56
     acts
    -0.56
     warr
    -0.54
    POSITIVE LOGITS
     Today
    3.80
    Today
    2.85
     TODAY
    2.42
    today
    2.34
     Tonight
    2.18
     today
    1.94
     Yesterday
    1.82
     Tomorrow
    1.81
    Tonight
    1.72
    Tomorrow
    1.69
    Activations Density 0.009%

    No Known Activations