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. 2-RES-JB
    6. 328
    Prev
    Next
    INDEX
    Explanations

    programming and coding terms related to dimensions, positions, errors, and syntax within code

    oai_token-act-pair · gpt-4-turbo

    CSS-related terms and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to programming and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arak
    -0.83
    peria
    -0.77
    HCR
    -0.75
    £ı
    -0.74
    ctuary
    -0.74
    judicial
    -0.74
    addons
    -0.70
    asio
    -0.69
    abouts
    -0.68
    llah
    -0.68
    POSITIVE LOGITS
    map
    0.83
     =>
    0.74
     width
    0.74
     Context
    0.73
     header
    0.73
    path
    0.72
     blob
    0.71
     Craw
    0.69
    ('
    0.68
     Bucket
    0.68
    Activations Density 0.338%

    No Known Activations