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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 986
    Prev
    Next
    INDEX
    Explanations

    the word "wine."

    oai_token-act-pair · gpt-4-turbo

    words related to the beverage "wine."

    oai_token-act-pair · gpt-3.5-turbo

    references to wine

    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
    aneous
    -0.77
    aneously
    -0.76
    uled
    -0.72
    ordinate
    -0.70
     WATCHED
    -0.70
    ulation
    -0.68
    ulu
    -0.67
    urtle
    -0.65
    DonaldTrump
    -0.64
     Fundamental
    -0.63
    POSITIVE LOGITS
     wine
    1.21
    wine
    1.17
     tasting
    1.16
     vinegar
    1.08
     grapes
    1.07
     cellar
    1.02
     tast
    1.02
     wines
    0.97
     vine
    0.95
     Wine
    0.87
    Activations Density 0.013%

    No Known Activations