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. 6-RES-JB
    6. 22592
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "documentary"

    oai_token-act-pair · gpt-3.5-turbo

    references to documentary films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.88
    hare
    -0.85
    hap
    -0.77
    ymes
    -0.77
    Commerce
    -0.72
    sembly
    -0.71
    cream
    -0.69
    ingers
    -0.69
    efficients
    -0.69
    uckles
    -0.68
    POSITIVE LOGITS
     filmmaker
    1.18
     documentary
    1.06
     filmmakers
    1.04
     filmmaking
    1.02
     film
    1.00
     documentaries
    0.92
    arily
    0.90
    film
    0.88
    arium
    0.88
     films
    0.85
    Activations Density 0.039%

    No Known Activations