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. 3131
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning specific academic journals or institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of academic or scientific disciplines, particularly "sciences."

    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
     bracket
    -0.76
     rough
    -0.67
     trailer
    -0.66
     tear
    -0.64
     knock
    -0.64
     flag
    -0.62
     lane
    -0.62
    key
    -0.61
     unofficial
    -0.61
     loose
    -0.61
    POSITIVE LOGITS
     Sciences
    3.80
     sciences
    2.88
     Science
    1.81
    Science
    1.67
    science
    1.46
    sci
    1.45
     Scientists
    1.38
     science
    1.33
     humanities
    1.32
     Biology
    1.27
    Activations Density 0.016%

    No Known Activations