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. 8-RES-JB
    6. 15419
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to computer programming, specifically C++ code snippets

    oai_token-act-pair · gpt-3.5-turbo

    programming concepts and syntax related to the C++ Standard Library

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osiris
    -0.82
    drops
    -0.79
    76561
    -0.77
     Seller
    -0.76
     Hilton
    -0.75
     Rewards
    -0.73
     Roz
    -0.73
    btn
    -0.72
     Rasmussen
    -0.71
    burse
    -0.71
    POSITIVE LOGITS
     Lisp
    1.13
     gcc
    1.10
     arithmetic
    1.07
     compiler
    1.07
     pointer
    1.06
     libraries
    1.02
     Haskell
    1.01
     bindings
    1.01
     integers
    1.00
     pointers
    0.99
    Activations Density 0.350%

    No Known Activations