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. 3-RES-JB
    6. 13842
    Prev
    Next
    INDEX
    Explanations

    words related to the action of 'filming'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "filming" and related activities in the context of movie production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.81
    dies
    -0.74
    abies
    -0.70
    abulary
    -0.68
    merce
    -0.68
    undai
    -0.68
    alg
    -0.67
    imb
    -0.67
    roe
    -0.67
    esse
    -0.67
    POSITIVE LOGITS
     filming
    0.97
     footage
    0.87
     crews
    0.81
     filmed
    0.80
     cameras
    0.75
     Camer
    0.74
     Kubrick
    0.72
     Studio
    0.72
     crew
    0.71
     studio
    0.71
    Activations Density 0.021%

    No Known Activations