© 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. 4967
    Prev
    Next
    INDEX
    Explanations

    terms related to story development, including conflicts, twists, and plot elements

    oai_token-act-pair · gpt-3.5-turbo

    elements related to narrative structure and storytelling conflicts

    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
    osate
    -0.80
     certified
    -0.77
    ickr
    -0.77
     unemploy
    -0.73
    software
    -0.72
    artisan
    -0.72
    heid
    -0.71
     Licensed
    -0.69
     Flickr
    -0.68
    ulic
    -0.68
    POSITIVE LOGITS
    Characters
    1.47
     plot
    1.38
     storyline
    1.38
     exposition
    1.37
     storylines
    1.35
     backstory
    1.32
     arcs
    1.31
     suspense
    1.25
     spoilers
    1.24
     climax
    1.23
    Activations Density 0.811%

    No Known Activations