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. 3798
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Hog."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Hog" or variations thereof

    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
    Catal
    -0.83
    cence
    -0.69
    Ross
    -0.69
    Marc
    -0.69
    negie
    -0.66
    cedes
    -0.64
     coord
    -0.64
    fecture
    -0.64
    elled
    -0.63
     Alexis
    -0.63
    POSITIVE LOGITS
     Hog
    3.45
     hog
    3.42
    hog
    2.91
     Hollow
    1.28
     Banner
    1.17
     Bee
    1.15
     Hound
    1.04
     bog
    1.03
    ogs
    1.02
     Hav
    1.02
    Activations Density 0.035%

    No Known Activations