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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15866
    Prev
    Next
    INDEX
    Explanations

    terms related to storytelling and production processes, possibly within the context of film or television

    oai_token-act-pair · gpt-3.5-turbo

    narratives that involve character development and interconnected storylines

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Welfare
    -0.74
     statist
    -0.72
    Charges
    -0.71
     depl
    -0.70
     racket
    -0.70
    Report
    -0.70
     Reported
    -0.70
    report
    -0.70
    iren
    -0.68
     REPORT
    -0.67
    POSITIVE LOGITS
    laughs
    1.34
     ['
    1.18
    Laughs
    1.13
     storytelling
    1.06
     creatively
    1.06
     ["
    1.05
     [
    0.98
    Theme
    0.97
     lyr
    0.97
     collaborations
    0.94
    Activations Density 0.728%

    No Known Activations