© 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 EvalsExportsinterp-engineNEWAPI 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. 14302
    Prev
    Next
    INDEX
    Explanations

    important events or entities related to film festivals or entertainment industry conventions

    oai_token-act-pair · gpt-3.5-turbo

    references to film and related events

    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
     multit
    -0.80
     overhead
    -0.76
     tread
    -0.75
     contraception
    -0.74
     nanop
    -0.74
     orth
    -0.73
     tooth
    -0.72
     replies
    -0.72
     positioning
    -0.72
     unfl
    -0.71
    POSITIVE LOGITS
     Festival
    1.61
    Fest
    1.56
     Expo
    1.52
     Fest
    1.42
     Awards
    1.26
     Gathering
    1.20
    fest
    1.18
     Summit
    1.18
     Show
    1.16
     Championships
    1.16
    Activations Density 0.212%

    No Known Activations