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. 11650
    Prev
    Next
    INDEX
    Explanations

    phrases related to beauty

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept and attributes of beauty

    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
    rust
    -0.70
    arbon
    -0.69
    sol
    -0.66
    imov
    -0.64
    eded
    -0.63
    renheit
    -0.62
    roman
    -0.61
    orum
    -0.61
    probably
    -0.61
    ern
    -0.60
    POSITIVE LOGITS
     beauty
    1.08
     pageant
    0.97
     contestant
    0.87
    iage
    0.78
     contests
    0.77
    issance
    0.77
     mathemat
    0.73
     queen
    0.72
     Mehran
    0.70
     Beauty
    0.69
    Activations Density 0.007%

    No Known Activations