© 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. 10-RES-JB
    11. 10337
    Prev
    Next
    INDEX
    Explanations

    terms related to interrupted dialogue, specifically with the structure "I said" followed by exclamatory punctuation

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or expressions that convey strong emotions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reprodu
    -0.71
     spectrum
    -0.70
     Skydragon
    -0.69
     MFT
    -0.69
     commercially
    -0.67
     range
    -0.65
     classification
    -0.65
     precip
    -0.64
     Mous
    -0.64
     shroud
    -0.64
    POSITIVE LOGITS
    ª
    1.50
    ł
    1.48
    ¹
    1.39
    Ķ
    1.30
    IJ
    1.30
    ³
    1.30
    ij
    1.28
    ©
    1.26
    ¡
    1.26
    ľ
    1.25
    Activations Density 0.124%

    No Known Activations