© 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. 20229
    Prev
    Next
    INDEX
    Explanations

    keywords related to historical subjects

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "History."

    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
    oad
    -0.70
     dotted
    -0.69
    rower
    -0.69
     targets
    -0.65
    inline
    -0.64
     gig
    -0.62
    quart
    -0.62
     align
    -0.61
    Magikarp
    -0.60
    percent
    -0.60
    POSITIVE LOGITS
     History
    3.84
    History
    2.72
     history
    2.64
    history
    2.56
     histories
    2.22
     Hist
    1.94
    ISTORY
    1.91
     Historical
    1.81
     historian
    1.57
    Hist
    1.54
    Activations Density 0.021%

    No Known Activations