© 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. 10-RES-JB
    11. 10686
    Prev
    Next
    INDEX
    Explanations

    mentions of the news outlet NBC with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the NBC network and its associated programming or news coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ellipt
    -0.77
    arians
    -0.75
     Riy
    -0.75
    ebook
    -0.69
    antly
    -0.69
    lang
    -0.69
     scrib
    -0.69
     quo
    -0.67
    adding
    -0.62
    wikipedia
    -0.61
    POSITIVE LOGITS
    Universal
    1.44
    SN
    1.16
     News
    1.04
    Sports
    1.01
     SPORTS
    0.99
    News
    0.98
     Sports
    0.98
     Universal
    0.93
    LA
    0.90
    NEWS
    0.86
    Activations Density 0.015%

    No Known Activations