© 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. 2-RES-JB
    11. 17436
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sip"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sip" and variations related to beverage consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ize
    -0.64
     Tycoon
    -0.63
     WB
    -0.62
    angel
    -0.62
    pedia
    -0.62
    izable
    -0.60
     overweight
    -0.59
     diarrhea
    -0.57
    taboola
    -0.57
    Bron
    -0.57
    POSITIVE LOGITS
     Seym
    0.88
    insula
    0.88
    vironment
    0.85
     sip
    0.83
    arta
    0.79
    bub
    0.78
    psey
    0.77
    ocratic
    0.77
    ratulations
    0.76
    indal
    0.75
    Activations Density 0.025%

    No Known Activations