© 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. 11-RES-JB
    11. 6524
    Prev
    Next
    INDEX
    Explanations

    keywords related to news, articles, and editorial content, especially focusing on the main story

    oai_token-act-pair · gpt-3.5-turbo

    references to the "main story" or central theme in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.74
    IDS
    -0.68
    IDs
    -0.67
    inav
    -0.62
    lihood
    -0.60
    ocene
    -0.60
    CI
    -0.60
     cumbers
    -0.57
     Cosponsors
    -0.57
    76561
    -0.57
    POSITIVE LOGITS
     story
    1.12
     Story
    0.84
    story
    0.83
     tale
    0.76
    Story
    0.75
     article
    0.72
     slideshow
    0.70
    stay
    0.69
     page
    0.67
     storyline
    0.66
    Activations Density 0.012%

    No Known Activations