© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24073
    Prev
    Next
    INDEX
    Explanations

    short descriptions of stories or narratives

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to narrative and storytelling

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     contrace
    -0.82
    ebus
    -0.80
     hardware
    -0.74
    bledon
    -0.73
    CPU
    -0.72
    lux
    -0.72
     bench
    -0.71
    ternity
    -0.70
    emouth
    -0.69
     occupancy
    -0.69
    POSITIVE LOGITS
     narrated
    1.32
     tales
    1.25
     tale
    1.22
    stories
    1.21
     stories
    1.17
     narr
    1.15
     unfolding
    1.15
     narratives
    1.13
     fiction
    1.09
     recounted
    1.09
    Activations Density 0.383%

    No Known Activations