© 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. 2-RES-JB
    11. 10408
    Prev
    Next
    INDEX
    Explanations

    phrases related to authors and co-authors

    oai_token-act-pair · gpt-3.5-turbo

    references to authorship or co-authors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EMS
    -0.76
     Pist
    -0.71
     wear
    -0.65
     Spears
    -0.64
     Leica
    -0.62
     Yard
    -0.62
     Maple
    -0.62
     Sabha
    -0.62
     Dortmund
    -0.61
    FW
    -0.61
    POSITIVE LOGITS
    itatively
    1.39
    itative
    1.17
    itarian
    1.04
    author
    0.98
    artist
    0.95
    itors
    0.94
    ournals
    0.92
    lisher
    0.91
    essee
    0.88
    alyst
    0.83
    Activations Density 0.011%

    No Known Activations