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. 7428
    Prev
    Next
    INDEX
    Explanations

    specific text ornaments or separators used in the text

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and titles of productions or works

    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
     tremend
    -0.94
     eleph
    -0.71
    aditional
    -0.68
    hement
    -0.68
     citiz
    -0.66
     oun
    -0.63
     occas
    -0.62
     representation
    -0.61
     grid
    -0.61
     undermin
    -0.61
    POSITIVE LOGITS
    ↵
    0.93
    ³³³³³³³³³³³³³³³³
    0.89
    ³³³
    0.77
    Merit
    0.76
    ³³³³³³³³
    0.75
    Premium
    0.72
    posted
    0.72
    minster
    0.72
    Population
    0.72
    Synopsis
    0.71
    Activations Density 0.248%

    No Known Activations