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. 1-RES-JB
    6. 12376
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "hog" at various frequencies

    oai_token-act-pair · gpt-3.5-turbo

    references to hogs and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     condem
    -0.80
    pai
    -0.77
     increment
    -0.73
    anguage
    -0.73
    Downloadha
    -0.73
     intervals
    -0.70
    eq
    -0.70
    ngth
    -0.69
     challeng
    -0.68
     contact
    -0.68
    POSITIVE LOGITS
     hog
    1.19
    hog
    1.10
    wash
    1.02
     Hog
    0.97
    gers
    0.87
    warts
    0.85
    alog
    0.79
    eral
    0.78
    glers
    0.78
    weed
    0.74
    Activations Density 0.007%

    No Known Activations