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. 3-RES-JB
    6. 22428
    Prev
    Next
    INDEX
    Explanations

    information related to government departments, officials, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to higher education and governmental institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dots
    -0.77
    lins
    -0.68
     fro
    -0.66
    auder
    -0.65
     shred
    -0.64
     toget
    -0.64
     silence
    -0.64
     bumper
    -0.64
    chev
    -0.63
    gart
    -0.63
    POSITIVE LOGITS
     Computing
    0.91
     Sciences
    0.90
     Journalism
    0.90
     Ethics
    0.89
     Agency
    0.88
     Preservation
    0.87
     Information
    0.87
     Federation
    0.87
     Affairs
    0.86
     Research
    0.84
    Activations Density 1.008%

    No Known Activations