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. 5913
    Prev
    Next
    INDEX
    Explanations

    locations or events related to Baton Rouge

    oai_token-act-pair · gpt-3.5-turbo

    references to Baton Rouge

    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
    essential
    -1.05
     measurable
    -0.64
     workload
    -0.64
     contributing
    -0.61
     function
    -0.59
    irk
    -0.58
     Citizen
    -0.58
    EP
    -0.57
     situational
    -0.57
    EFF
    -0.56
    POSITIVE LOGITS
     Rouge
    4.46
     Gou
    1.04
    ossier
    0.96
     Janeiro
    0.95
    thia
    0.94
     Belle
    0.93
     Aires
    0.90
     Lauder
    0.90
     Royale
    0.89
    aire
    0.87
    Activations Density 0.017%

    No Known Activations