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. 9-RES-JB
    6. 406
    Prev
    Next
    INDEX
    Explanations

    titles or headings starting with "As the" followed by a noun or noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    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
     besides
    -0.91
    fab
    -0.91
    Ò
    -0.87
    abouts
    -0.81
    neg
    -0.77
    puff
    -0.72
    ca
    -0.72
     whatsoever
    -0.71
    bg
    -0.70
    ibl
    -0.70
    POSITIVE LOGITS
     result
    1.14
     centerpiece
    0.94
     crow
    0.93
     sun
    0.90
     tide
    0.88
     Inquis
    0.86
     tides
    0.85
     oldest
    0.85
     youngest
    0.85
     sole
    0.82
    Activations Density 0.100%

    No Known Activations