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. 11-RES-JB
    6. 19907
    Prev
    Next
    INDEX
    Explanations

    references to various forms of entertainment media such as television shows, movies, and music

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of media and entertainment, particularly television and movies

    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
    etsk
    -0.80
    nir
    -0.73
    sole
    -0.71
    ework
    -0.69
    utan
    -0.67
    METHOD
    -0.67
    nih
    -0.66
    west
    -0.66
    Serv
    -0.66
    apache
    -0.65
    POSITIVE LOGITS
     television
    1.44
     documentaries
    1.43
     movies
    1.39
     DVDs
    1.38
     magazines
    1.36
     tv
    1.36
     TV
    1.35
     novels
    1.34
     films
    1.32
     radio
    1.31
    Activations Density 0.243%

    No Known Activations