© 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. 12358
    Prev
    Next
    INDEX
    Explanations

    adverbs intensifying the degree or strength of the following words

    oai_token-act-pair · gpt-3.5-turbo

    the adverb "very" and its variations, indicating an emphasis or intensification of other descriptors

    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
    olor
    -0.77
    osal
    -0.75
    adelphia
    -0.75
    ensis
    -0.69
    sburgh
    -0.68
    orno
    -0.65
    ourses
    -0.64
    imus
    -0.63
    iture
    -0.63
    esan
    -0.62
    POSITIVE LOGITS
     informative
    0.77
     rarely
    0.74
     similar
    0.74
     important
    0.74
     different
    0.73
     seldom
    0.73
     handy
    0.72
     rare
    0.71
     expensive
    0.70
    STEM
    0.70
    Activations Density 0.065%

    No Known Activations