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. 8-RES-JB
    6. 16549
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical or metaphorical acts of force

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving physical or metaphorical slaps in the face or wrist, indicating feelings of criticism or punishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.71
    leys
    -0.67
     Dian
    -0.64
    xual
    -0.64
    alg
    -0.63
    erness
    -0.62
    ibles
    -0.62
    fol
    -0.61
    oret
    -0.61
     bedrooms
    -0.61
    POSITIVE LOGITS
    ãĤ½
    0.74
     shoulder
    0.71
     heels
    0.68
    ooth
    0.68
    EGA
    0.67
     cheek
    0.67
    ón
    0.66
     forehead
    0.66
     os
    0.65
    orsi
    0.65
    Activations Density 0.195%

    No Known Activations