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. 2-RES-JB
    6. 4780
    Prev
    Next
    INDEX
    Explanations

    keywords related to soap, such as "soap opera", "soap production", and "soap smells"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of soap and related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etermined
    -0.71
    alez
    -0.69
    trl
    -0.68
    uding
    -0.68
    sen
    -0.67
    places
    -0.65
    orders
    -0.64
    restricted
    -0.61
     sworn
    -0.60
    ooming
    -0.60
    POSITIVE LOGITS
     soap
    1.17
     opera
    1.07
     oper
    0.98
    utical
    0.82
    ãĤ¦ãĤ¹
    0.81
    bub
    0.81
    glers
    0.79
     Bubble
    0.78
    bowl
    0.77
     è£ıè
    0.73
    Activations Density 0.007%

    No Known Activations