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. 0-RES-JB
    6. 10801
    Prev
    Next
    INDEX
    Explanations

    code elements signaled by the "cd" keyword

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific code or directory references in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cd
    -0.80
     sudo
    -0.68
     Must
    -0.67
     mark
    -0.66
     Jobs
    -0.65
     Grayson
    -0.64
     Manafort
    -0.64
     nominations
    -0.62
     Nicaragua
    -0.58
     Iran
    -0.58
    POSITIVE LOGITS
    cd
    2.79
    pd
    1.15
    jad
    1.00
    phia
    0.99
    cs
    0.98
    ecd
    0.92
    mary
    0.91
    dd
    0.88
    chron
    0.88
    ema
    0.86
    Activations Density 0.003%

    No Known Activations