Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18898
    Prev
    Next
    INDEX
    Explanations

    programming languages and related terms, especially focusing on Lisp, C++, and Rust

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.70
    rha
    -0.64
     exha
    -0.62
     discounts
    -0.62
     bonuses
    -0.62
    iquid
    -0.61
     Leia
    -0.61
    stre
    -0.61
    awei
    -0.60
     HIP
    -0.60
    POSITIVE LOGITS
     bindings
    1.05
     equivalents
    0.93
    Script
    0.90
    Reader
    0.86
     runtime
    0.86
     Programming
    0.85
    API
    0.84
     programmers
    0.84
    istani
    0.83
    Bench
    0.83
    Activations Density 0.078%

    No Known Activations