© 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. 1-RES-JB
    11. 14391
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "oil"

    oai_token-act-pair · gpt-3.5-turbo

    references to the oil industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.85
    RON
    -0.83
    rons
    -0.82
     Inv
    -0.80
     Dare
    -0.75
    BY
    -0.74
     Cox
    -0.74
    EMBER
    -0.73
    é¾įå
    -0.73
     Try
    -0.72
    POSITIVE LOGITS
     oil
    1.21
    Oil
    1.02
    seed
    1.01
    oil
    1.00
     slic
    0.99
     Oil
    0.96
     sands
    0.94
     tanker
    0.88
     drilling
    0.88
     refining
    0.88
    Activations Density 0.016%

    No Known Activations