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. 3-RES-JB
    6. 7852
    Prev
    Next
    INDEX
    Explanations

    technical terms related to coding such as debuggers, parsers, translators, and converters

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to debugging and parsing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ories
    -0.82
    ippi
    -0.78
     Pradesh
    -0.77
    itions
    -0.75
    reek
    -0.74
    itional
    -0.73
    ured
    -0.72
    romy
    -0.71
    ori
    -0.70
    rawn
    -0.69
    POSITIVE LOGITS
     extraord
    0.96
     converter
    0.84
     builder
    0.79
     plugin
    0.77
     Clicker
    0.75
    GUI
    0.73
    oute
    0.70
     addon
    0.69
     Launcher
    0.67
     Scotia
    0.67
    Activations Density 0.108%

    No Known Activations