© 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. 2-RES-JB
    11. 5250
    Prev
    Next
    INDEX
    Explanations

    acronyms related to natural gas (NG)

    oai_token-act-pair · gpt-3.5-turbo

    references to natural gas (NG) and its related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.79
    lished
    -0.73
    lain
    -0.70
    advert
    -0.66
    self
    -0.64
    andowski
    -0.63
    iona
    -0.63
    ãĥī
    -0.62
    hold
    -0.62
    ãĥ¡
    -0.62
    POSITIVE LOGITS
    NG
    1.10
    emonic
    0.87
    SS
    0.81
    culosis
    0.75
    IVERS
    0.75
    guyen
    0.75
    elist
    0.74
    OV
    0.74
    LR
    0.73
    OD
    0.73
    Activations Density 0.005%

    No Known Activations