© 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. 22871
    Prev
    Next
    INDEX
    Explanations

    comparative terms indicating a larger quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    the word "more" and its implications in various contexts

    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
    anka
    -0.76
    arta
    -0.71
    rade
    -0.70
    nor
    -0.67
    iku
    -0.66
    eat
    -0.65
    erno
    -0.65
    ibi
    -0.63
    urn
    -0.62
    etz
    -0.62
    POSITIVE LOGITS
     more
    2.53
     fewer
    1.84
     MORE
    1.76
     less
    1.75
    more
    1.73
     clearer
    1.59
     stronger
    1.58
     More
    1.57
     harder
    1.56
    More
    1.56
    Activations Density 0.158%

    No Known Activations