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. 8-RES-JB
    6. 5361
    Prev
    Next
    INDEX
    Explanations

    phrases related to sound effects or onomatopoeic words

    oai_token-act-pair · gpt-3.5-turbo

    references to song titles or popular musical phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Misc
    repeating token feature

    No Comments

    Negative Logits
    Newsletter
    -0.86
     seiz
    -0.72
    Untitled
    -0.71
    ãĥ´
    -0.69
     guiActiveUn
    -0.69
    Īè
    -0.65
    zanne
    -0.64
    ãĥĩãĤ£
    -0.63
    emouth
    -0.63
    ï¸ı
    -0.63
    POSITIVE LOGITS
    ingen
    0.69
     Coyotes
    0.68
     Kenobi
    0.66
     Kinnikuman
    0.65
     IU
    0.65
    lar
    0.64
     Rebels
    0.64
     OT
    0.62
    loo
    0.58
     Wink
    0.57
    Activations Density 0.209%

    No Known Activations