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. 14273
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and programming-related concepts

    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
    vol
    -0.91
    ous
    -0.88
    ously
    -0.79
    ãģ®éŃĶ
    -0.73
    auld
    -0.72
    same
    -0.62
     Lowe
    -0.61
     vol
    -0.61
    va
    -0.60
    zzi
    -0.60
    POSITIVE LOGITS
    matically
    0.95
     languages
    0.88
     Languages
    0.85
    eering
    0.80
     programming
    0.78
     chops
    0.78
    mers
    0.77
     interfaces
    0.77
    matic
    0.76
    isphere
    0.74
    Activations Density 0.010%

    No Known Activations