© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 18991
    Prev
    Next
    INDEX
    Explanations

    words related to drinks and beverages with special emphasis on "Kool-Aid"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to a specific beverage brand or product

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Debor
    -0.69
     Oro
    -0.68
    aldi
    -0.68
     proble
    -0.64
     Alv
    -0.63
    henko
    -0.62
    URA
    -0.61
    Domin
    -0.60
    ãģ¦
    -0.60
     Stras
    -0.59
    POSITIVE LOGITS
    ittle
    1.09
    igans
    1.05
    ibrary
    1.01
    igan
    0.95
    ounge
    0.92
    ftime
    0.91
    ingen
    0.91
    isted
    0.89
    wyn
    0.88
    ition
    0.88
    Activations Density 0.034%

    No Known Activations