Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 14247
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology setups or configurations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "setup" in various contexts

    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
    letters
    -0.75
    African
    -0.68
    Asian
    -0.67
     Newsp
    -0.67
    severe
    -0.65
    utra
    -0.65
     Wad
    -0.65
    arine
    -0.64
     newspapers
    -0.64
    food
    -0.63
    POSITIVE LOGITS
     setup
    3.63
     Setup
    2.62
     setups
    2.40
    Setup
    2.27
    setup
    2.17
     configuration
    1.55
     layout
    1.36
     configure
    1.32
     configured
    1.27
     settings
    1.25
    Activations Density 0.018%

    No Known Activations