© 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. 11-RES-JB
    11. 12921
    Prev
    Next
    INDEX
    Explanations

    phrases relating to creativity and collaboration in the context of creating something new

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to collaboration and creation in artistic projects

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    oslav
    -0.73
    bard
    -0.71
     nurs
    -0.69
    cler
    -0.69
     abolished
    -0.69
    Assistant
    -0.68
     lax
    -0.68
    BSD
    -0.68
     resorted
    -0.68
    Setup
    -0.67
    POSITIVE LOGITS
     storytelling
    1.69
     audiences
    1.39
     cinematic
    1.37
     immersive
    1.32
     filmmaking
    1.26
     cinema
    1.23
     storylines
    1.22
     genre
    1.21
     filmmakers
    1.20
     narratives
    1.18
    Activations Density 0.506%

    No Known Activations