© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 12513
    Prev
    Next
    INDEX
    Explanations

    words related to luxury goods or high-end fashion

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "lux" specifically in the context of luxury or as part of related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansom
    -0.75
    wart
    -0.75
    à¨
    -0.74
    à©
    -0.68
    stal
    -0.68
    anguage
    -0.63
    ¶ħ
    -0.62
     Turing
    -0.62
    ¢
    -0.61
    crow
    -0.60
    POSITIVE LOGITS
    iliary
    1.33
    ury
    1.25
    edo
    1.14
    uries
    1.13
    urious
    1.10
     Pavilion
    0.89
    uria
    0.87
    xes
    0.85
    imately
    0.83
    avier
    0.83
    Activations Density 0.027%

    No Known Activations