Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9572
    Prev
    Next
    INDEX
    Explanations

    references to filming locations

    oai_token-act-pair · gpt-3.5-turbo

    references to filming locations in movies

    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
    Merit
    -1.04
    uyomi
    -0.88
    reprene
    -0.83
    soType
    -0.81
    galitarian
    -0.78
    arma
    -0.74
    coin
    -0.74
    ickle
    -0.73
    erenn
    -0.73
     coh
    -0.72
    POSITIVE LOGITS
     filming
    1.65
     footage
    1.56
     camer
    1.54
     filmed
    1.50
     cinem
    1.40
     scenes
    1.38
     camera
    1.30
     Kubrick
    1.26
     cinematic
    1.22
     cameras
    1.21
    Activations Density 0.861%

    No Known Activations