© 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. 8-RES-JB
    11. 20314
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of wine

    oai_token-act-pair · gpt-3.5-turbo

    the word "wine" and its variations, indicating a focus on wine-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.76
    aneous
    -0.73
    aneously
    -0.70
    ilitary
    -0.69
     unnecess
    -0.69
    rencies
    -0.67
    uled
    -0.67
    ulation
    -0.66
    uli
    -0.66
    urtle
    -0.64
    POSITIVE LOGITS
    yard
    1.12
     grapes
    1.09
    yards
    1.08
     tasting
    1.04
     vinegar
    1.02
     cellar
    0.96
    gard
    0.90
     wine
    0.88
    gars
    0.86
    fruit
    0.85
    Activations Density 0.041%

    No Known Activations