© 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. 0-RES-JB
    11. 1880
    Prev
    Next
    INDEX
    Explanations

    words related to generators

    oai_token-act-pair · gpt-3.5-turbo

    references to generators and related energy-producing equipment

    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
     openly
    -0.70
     candid
    -0.67
     Velvet
    -0.67
    hid
    -0.66
    bull
    -0.66
    Lyn
    -0.65
    Asian
    -0.64
     Mens
    -0.63
     Tus
    -0.62
    eness
    -0.62
    POSITIVE LOGITS
     generator
    3.90
     generators
    3.51
     Generator
    2.88
     transformer
    1.59
     generating
    1.42
     compressor
    1.34
    Gener
    1.33
     turbine
    1.32
     builder
    1.29
    gener
    1.28
    Activations Density 0.016%

    No Known Activations