Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2971
    Prev
    Next
    INDEX
    Explanations

    words related to aesthetics and beauty

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to aesthetic qualities and beauty

    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
    etime
    -0.78
    sen
    -0.75
    Account
    -0.73
    road
    -0.73
    king
    -0.69
    fortune
    -0.69
    load
    -0.68
    idden
    -0.68
    few
    -0.67
    cloth
    -0.67
    POSITIVE LOGITS
     aesthetic
    1.17
     aesthetics
    1.03
     sensibilities
    1.01
     aest
    0.88
    hetically
    0.85
     flair
    0.85
    Þ
    0.78
     sophistication
    0.76
     advis
    0.75
     splend
    0.75
    Activations Density 0.010%

    No Known Activations