© 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. 3-RES-JB
    11. 1929
    Prev
    Next
    INDEX
    Explanations

    the word "are" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "are," indicating emphasis on being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omez
    -0.69
    ingen
    -0.67
    uration
    -0.65
    imating
    -0.61
    oting
    -0.59
    allery
    -0.59
    ured
    -0.59
    ertodd
    -0.59
    imation
    -0.58
    OOL
    -0.58
    POSITIVE LOGITS
    nce
    1.03
    nces
    1.01
    tsky
    1.00
    tto
    0.97
    nda
    0.88
    tta
    0.87
    nt
    0.86
    nd
    0.83
    zza
    0.82
    lli
    0.81
    Activations Density 0.019%

    No Known Activations