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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 21474
    Prev
    Next
    INDEX
    Explanations

    references to characters and elements from the Star Wars universe

    oai_token-act-pair · gpt-3.5-turbo

    references to the Jedi and their related characters or concepts

    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
     Vog
    -0.67
    iard
    -0.63
    esters
    -0.63
     IGF
    -0.62
    debian
    -0.62
     iP
    -0.62
     @@
    -0.62
    anguages
    -0.61
     LIA
    -0.61
    trak
    -0.61
    POSITIVE LOGITS
     Skywalker
    1.17
     Awakens
    0.96
     Vader
    0.95
     Kenobi
    0.94
     Trooper
    0.87
     Solo
    0.86
     Rebels
    0.85
     lightsaber
    0.82
     trooper
    0.82
     Leia
    0.79
    Activations Density 0.130%

    No Known Activations