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. 1-RES-JB
    6. 9194
    Prev
    Next
    INDEX
    Explanations

    specific patterns of characters that are not textual words

    oai_token-act-pair · gpt-3.5-turbo

    blockbuster movies and their box office earnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.72
    ĸļ
    -0.62
     undermin
    -0.59
     undet
    -0.58
    mares
    -0.57
     lifes
    -0.55
     honoured
    -0.54
     scrap
    -0.54
     submar
    -0.54
     citiz
    -0.53
    POSITIVE LOGITS
    Advertisement
    0.73
    Anonymous
    0.72
    ³³³³³³³³³³³³³³³³
    0.71
    ³³³³
    0.71
    Recommended
    0.69
    ONSORED
    0.69
    VERTISEMENT
    0.69
    ³³³
    0.67
    ³³³³³³³³
    0.67
    Interest
    0.67
    Activations Density 1.327%

    No Known Activations