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. 6-RES-JB
    6. 22963
    Prev
    Next
    INDEX
    Explanations

    keywords and codes related to programming and software development

    oai_token-act-pair · gpt-3.5-turbo

    coding terminology and variable names used in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     politic
    -0.77
     wat
    -0.75
     Afric
    -0.72
     jihad
    -0.69
    Ùĩ
    -0.69
     bir
    -0.69
     Tsarnaev
    -0.68
     Benghazi
    -0.68
     Sudan
    -0.67
     Accountability
    -0.67
    POSITIVE LOGITS
    ints
    0.91
    uler
    0.89
    ailed
    0.89
    ights
    0.89
    odes
    0.88
    itted
    0.88
    ocations
    0.86
    otation
    0.85
    ummy
    0.85
    ute
    0.84
    Activations Density 0.363%

    No Known Activations