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. 10849
    Prev
    Next
    INDEX
    Explanations

    words in a foreign language that are not part of the standard English alphabet

    oai_token-act-pair · gpt-3.5-turbo

    specific non-Latin characters or symbols

    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
    iture
    -0.68
     Pers
    -0.66
     model
    -0.66
     respectively
    -0.65
     Pere
    -0.64
     net
    -0.64
     roll
    -0.64
     Cly
    -0.62
     PE
    -0.61
     Blank
    -0.61
    POSITIVE LOGITS
    Ń
    4.48
    ¬
    2.32
    ®
    2.09
    ¯
    1.95
    «
    1.86
    µ
    1.79
    º
    1.73
    ³
    1.72
    ¸
    1.70
    ī
    1.69
    Activations Density 0.001%

    No Known Activations