© 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. 8-RES-JB
    11. 19425
    Prev
    Next
    INDEX
    Explanations

    adverbs expressing deep emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of deep emotions, particularly those related to sadness, gratitude, and pride

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trickle
    -0.74
     supposedly
    -0.71
     looms
    -0.71
     vanish
    -0.68
     Advertisement
    -0.66
     Pastebin
    -0.65
     disappear
    -0.65
    VERTISEMENT
    -0.63
     vanished
    -0.63
     roadside
    -0.63
    POSITIVE LOGITS
     grateful
    1.29
     thankful
    1.23
     regret
    1.19
     glad
    1.19
     gratitude
    1.07
     saddened
    1.04
     amazed
    1.04
     admiration
    1.01
     regrets
    0.99
     wish
    0.98
    Activations Density 0.277%

    No Known Activations