© 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. 0-RES-JB
    11. 14923
    Prev
    Next
    INDEX
    Explanations

    adjectives related to comparison or equality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "equally."

    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
    ua
    -0.82
    Person
    -0.64
    oa
    -0.64
    arta
    -0.62
    info
    -0.61
     Properties
    -0.61
     Journal
    -0.60
    ature
    -0.60
    debug
    -0.58
     Newsletter
    -0.57
    POSITIVE LOGITS
     equally
    3.64
     similarly
    1.77
     evenly
    1.68
     uniformly
    1.49
     equal
    1.47
     likewise
    1.29
     universally
    1.25
    equal
    1.24
     identical
    1.20
     simultaneously
    1.18
    Activations Density 0.010%

    No Known Activations