© 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. 4-RES-JB
    11. 18642
    Prev
    Next
    INDEX
    Explanations

    adverbs emphasizing extremity

    oai_token-act-pair · gpt-3.5-turbo

    adjectives expressing a strong degree of emphasis or intensity

    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
    ioch
    -0.90
    hao
    -0.86
    hops
    -0.84
    arters
    -0.76
     Occupations
    -0.74
    anwhile
    -0.73
    imore
    -0.72
    iers
    -0.71
     cigars
    -0.70
    chedel
    -0.68
    POSITIVE LOGITS
    ingly
    0.90
    ãĤ¦ãĤ¹
    0.80
    ãĥŀ
    0.74
    antly
    0.73
    ãĥIJ
    0.72
    ulously
    0.69
    ä¿
    0.69
    important
    0.68
     bewild
    0.68
    è¯
    0.67
    Activations Density 0.019%

    No Known Activations