© 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. 7624
    Prev
    Next
    INDEX
    Explanations

    words related to biofuels

    oai_token-act-pair · gpt-3.5-turbo

    references to biofuels and related substances

    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
     Rapp
    -0.84
     Brune
    -0.71
    ollah
    -0.69
     Nicarag
    -0.68
     Guant
    -0.68
     Revolutionary
    -0.67
     Chong
    -0.67
     Sho
    -0.66
     IRA
    -0.64
     Hawai
    -0.64
    POSITIVE LOGITS
    achy
    2.63
    aline
    1.75
    apy
    1.72
    leon
    1.54
    fu
    1.48
    yth
    1.45
    mia
    1.24
     Bates
    1.23
    ansom
    1.09
    bos
    1.06
    Activations Density 0.054%

    No Known Activations