© 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. 0-RES-JB
    11. 8276
    Prev
    Next
    INDEX
    Explanations

    websites or platforms with "live" in the name

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "live" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cu
    -0.69
     sack
    -0.66
     powers
    -0.65
     Boat
    -0.64
     trenches
    -0.64
     Dunn
    -0.64
     Counsel
    -0.64
     equ
    -0.62
     Treasury
    -0.62
     passage
    -0.61
    POSITIVE LOGITS
    live
    4.54
    Live
    2.45
     live
    1.79
     LIVE
    1.76
     Live
    1.76
    living
    1.39
    lived
    1.27
    liv
    1.21
     livest
    1.11
    life
    1.09
    Activations Density 0.015%

    No Known Activations