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. 0-RES-JB
    6. 23071
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to computer programming languages and symbols

    oai_token-act-pair · gpt-3.5-turbo

    currency symbols and associated pricing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visualization
    -0.66
     Tribe
    -0.65
     HuffPost
    -0.64
     concentration
    -0.62
     controlled
    -0.59
     tribal
    -0.58
    ressive
    -0.58
     suppress
    -0.58
     Biological
    -0.57
     suppression
    -0.57
    POSITIVE LOGITS
    âĤ¬
    4.49
     âĤ¬
    2.57
    £
    2.20
     euros
    1.71
     EUR
    1.56
     £
    1.53
     Euros
    1.43
    $.
    1.42
    $
    1.41
    euro
    1.39
    Activations Density 0.011%

    No Known Activations