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. 10-RES-JB
    6. 8871
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming, such as "compile", "profiling", "executable", "debug", "compiler", "testing", "translation", "build", "deploy", "environment"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coding and compilation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hilton
    -0.80
    ometown
    -0.72
     forfeit
    -0.69
    opol
    -0.69
     Mechanical
    -0.66
    oeuv
    -0.65
     Eleven
    -0.64
    acus
    -0.64
     Adult
    -0.63
    ippery
    -0.63
    POSITIVE LOGITS
     suites
    1.05
     dependencies
    1.04
     runtime
    1.02
    pkg
    0.99
     compilation
    0.98
     plugins
    0.97
     binaries
    0.97
     tools
    0.96
     compiler
    0.96
     sandbox
    0.96
    Activations Density 0.134%

    No Known Activations