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. 11-RES-JB
    6. 15285
    Prev
    Next
    INDEX
    Explanations

    phrases related to aesthetic judgment, especially regarding appearance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating judgment or evaluation of situations or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pora
    -0.80
    only
    -0.78
    successfully
    -0.77
    rimination
    -0.75
    afort
    -0.73
    even
    -0.68
    often
    -0.67
     extensively
    -0.65
    etheus
    -0.65
     indeed
    -0.64
    POSITIVE LOGITS
    ifiable
    0.81
     coincidence
    0.78
     darn
    0.75
    cause
    0.72
    fuck
    0.70
     plain
    0.70
     wow
    0.69
     fucking
    0.68
     luck
    0.67
     fun
    0.67
    Activations Density 0.240%

    No Known Activations