© 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. 4923
    Prev
    Next
    INDEX
    Explanations

    titles of articles, books, or pieces of writing

    oai_token-act-pair · gpt-3.5-turbo

    instances of titles in the text

    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
    elta
    -0.68
     flexibility
    -0.62
     advantage
    -0.62
    ints
    -0.62
    gio
    -0.59
    fast
    -0.58
    ources
    -0.58
    elsen
    -0.57
     accommodation
    -0.57
    mite
    -0.56
    POSITIVE LOGITS
     titled
    3.52
     entitled
    2.32
     headlined
    1.90
    itled
    1.90
     dubbed
    1.53
     labeled
    1.45
     termed
    1.34
     authored
    1.34
     dated
    1.34
     named
    1.34
    Activations Density 0.013%

    No Known Activations