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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7438
    Prev
    Next
    INDEX
    Explanations

    words related to luxury and lavishness

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "lavish" and its variations, indicating opulence or excessive wealth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥª
    -0.72
    sein
    -0.68
    roads
    -0.67
    POS
    -0.67
    figure
    -0.67
    PRES
    -0.67
    PDATE
    -0.66
    BOOK
    -0.66
    Christ
    -0.65
    change
    -0.64
    POSITIVE LOGITS
    ishly
    1.08
    iolet
    1.04
    endar
    1.04
     Lav
    1.02
    atories
    1.01
    igne
    0.95
    atory
    0.92
    adium
    0.92
    anca
    0.90
    acy
    0.89
    Activations Density 0.016%

    No Known Activations