© 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 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. 10-RES-JB
    11. 4329
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of alcohol, particularly wine

    oai_token-act-pair · gpt-3.5-turbo

    mentions of wine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilitary
    -0.79
    ulation
    -0.76
    aneous
    -0.73
    aneously
    -0.71
    ospace
    -0.71
     Occupations
    -0.67
    ULAR
    -0.66
     Bangl
    -0.65
    Tur
    -0.64
     WATCHED
    -0.64
    POSITIVE LOGITS
     grapes
    1.26
     tasting
    1.23
     cellar
    1.23
     vinegar
    1.23
     wine
    1.13
    wine
    1.11
     tast
    1.04
     bottles
    1.02
     grape
    1.02
     wines
    0.98
    Activations Density 0.033%

    No Known Activations