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. 10419
    Prev
    Next
    INDEX
    Explanations

    countries and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and organizations

    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
    unless
    -0.67
    ',"
    -0.62
    '."
    -0.62
     stupidity
    -0.61
    ...?
    -0.60
    .'"
    -0.56
     unless
    -0.55
     rubbish
    -0.55
    doesn
    -0.55
    agus
    -0.54
    POSITIVE LOGITS
    âĢ
    1.44
     âĢ
    1.23
    / 
    1.09
    âĢł
    1.07
    ãĢ
    1.06
    âĹ
    1.03
    ï¸
    1.03
    âģ
    0.97
    âľ
    0.93
    âĸº
    0.92
    Activations Density 1.074%

    No Known Activations