© 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. 4-RES-JB
    11. 2509
    Prev
    Next
    INDEX
    Explanations

    information related to diesel fuel and pricing

    oai_token-act-pair · gpt-3.5-turbo

    references to diesel fuel and related terms

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

    No Comments

    Negative Logits
    xual
    -0.94
    olulu
    -0.93
     skelet
    -0.78
     Kinnikuman
    -0.78
    yip
    -0.77
    onew
    -0.76
    odore
    -0.74
    amaru
    -0.69
    ellen
    -0.69
    oning
    -0.68
    POSITIVE LOGITS
    punk
    1.05
     fumes
    0.93
     diesel
    0.87
    jet
    0.86
     fuel
    0.80
    wagon
    0.75
     exhaust
    0.75
     emissions
    0.71
     locom
    0.71
    minist
    0.71
    Activations Density 0.006%

    No Known Activations