© 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. 0-RES-JB
    11. 2032
    Prev
    Next
    INDEX
    Explanations

    contrasts or differences in statements or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contrast" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hers
    -0.72
    ickets
    -0.69
    busters
    -0.66
    hop
    -0.66
    Got
    -0.66
    akers
    -0.66
    mons
    -0.64
    uthor
    -0.64
     owns
    -0.62
    arant
    -0.61
    POSITIVE LOGITS
     contrast
    3.80
     contrasts
    2.50
     Contrast
    2.34
     contrasted
    2.10
     contrasting
    1.91
     comparison
    1.78
     juxtap
    1.61
     distinction
    1.33
     contradiction
    1.32
     analogy
    1.27
    Activations Density 0.015%

    No Known Activations