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. 3236
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical systems or products

    oai_token-act-pair · gpt-3.5-turbo

    references to various systems

    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
     diamonds
    -0.71
     bapt
    -0.68
    hur
    -0.66
    forth
    -0.65
     fet
    -0.64
    ulton
    -0.64
     bust
    -0.62
     delight
    -0.62
    flame
    -0.62
     Harley
    -0.61
    POSITIVE LOGITS
     System
    3.72
    System
    2.61
     system
    2.36
     SYSTEM
    2.34
    system
    2.32
     Systems
    2.26
     systems
    1.84
    ystem
    1.37
    Sys
    1.33
     Program
    1.19
    Activations Density 0.017%

    No Known Activations