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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 22044
    Prev
    Next
    INDEX
    Explanations

    locations or references to "Napa Valley."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Nap" or "Napa," likely indicating a focus on the Napa Valley region

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

    No Comments

    Negative Logits
     Gemini
    -0.86
    DonaldTrump
    -0.79
     Carbuncle
    -0.76
    ³³³
    -0.69
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.67
    âĸ¬âĸ¬
    -0.67
    EVA
    -0.67
    âĢ¢âĢ¢
    -0.66
    ×Ļ×
    -0.66
    UCT
    -0.66
    POSITIVE LOGITS
    oleon
    1.39
    olit
    1.32
    alm
    1.26
    olitan
    1.21
    erville
    1.05
    rose
    0.93
    oton
    0.92
    Nap
    0.91
    oli
    0.90
    oline
    0.89
    Activations Density 0.009%

    No Known Activations