© 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. 9-RES-JB
    11. 15659
    Prev
    Next
    INDEX
    Explanations

    technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "technology" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.73
    hyde
    -0.72
    heit
    -0.70
    lein
    -0.69
    ibli
    -0.65
     Gamb
    -0.62
    aukee
    -0.62
    atory
    -0.62
    stad
    -0.62
    ãĤ¡
    -0.62
    POSITIVE LOGITS
     advancements
    1.04
    ologies
    0.99
     innovation
    0.97
     savvy
    0.91
     innov
    0.88
    Crunch
    0.87
     innovations
    0.86
     gadgets
    0.82
     powering
    0.81
     upgr
    0.81
    Activations Density 0.039%

    No Known Activations