© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16497
    Prev
    Next
    INDEX
    Explanations

    descriptions of moments or scenes from different forms of media, including films, TV shows, comics, and books

    oai_token-act-pair · gpt-3.5-turbo

    elements related to emotional moments in storytelling

    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
    BUS
    -0.80
    software
    -0.78
    METHOD
    -0.78
    ORTS
    -0.77
    Register
    -0.76
     publishes
    -0.75
    ebook
    -0.74
    ournaments
    -0.74
    profits
    -0.72
     administr
    -0.71
    POSITIVE LOGITS
     cameo
    1.75
     flashback
    1.45
     scene
    1.39
     scenes
    1.32
     mont
    1.27
     clip
    1.20
     teaser
    1.18
     gag
    1.17
     sequence
    1.16
     Scenes
    1.14
    Activations Density 0.509%

    No Known Activations