© 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. 4-RES-JB
    11. 1670
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    references to "other" as a way to categorize or distinguish items

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

    No Comments

    Negative Logits
     1915
    -0.67
    zai
    -0.64
     2024
    -0.62
     1863
    -0.61
     1972
    -0.60
     1922
    -0.60
     quota
    -0.60
     1937
    -0.59
     1962
    -0.59
     1965
    -0.58
    POSITIVE LOGITS
    worldly
    1.93
    parts
    0.92
    wise
    0.92
    swer
    0.87
    quickShipAvailable
    0.84
    types
    0.81
    world
    0.78
    omon
    0.77
     aspects
    0.74
    oggles
    0.73
    Activations Density 0.100%

    No Known Activations