© 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. 7-RES-JB
    11. 23075
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or contrasts between two ideas or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.69
     Kard
    -0.67
    ells
    -0.66
     Niet
    -0.65
     Carnival
    -0.65
     Quake
    -0.64
    boys
    -0.61
    haven
    -0.61
    oufl
    -0.60
     Dirt
    -0.59
    POSITIVE LOGITS
    itably
    0.95
    entimes
    0.79
     necessarily
    0.75
    isons
    0.73
    onent
    0.70
    acles
    0.70
    lihood
    0.69
    ively
    0.68
    lectic
    0.66
     materially
    0.65
    Activations Density 0.019%

    No Known Activations