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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7981
    Prev
    Next
    INDEX
    Explanations

    dates or time-related words

    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 @ 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
     foot
    -0.74
     missing
    -0.69
     double
    -0.67
     possibly
    -0.67
     arms
    -0.66
     append
    -0.63
     chest
    -0.62
     dupl
    -0.61
     verbal
    -0.60
     similar
    -0.60
    POSITIVE LOGITS
    Today
    3.66
     Today
    2.75
    today
    2.48
    Tonight
    2.34
    Yesterday
    2.14
    Tomorrow
    2.05
     today
    1.83
     TODAY
    1.77
     Tonight
    1.66
     Yesterday
    1.55
    Activations Density 0.009%

    No Known Activations