© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24086
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "petroleum"

    oai_token-act-pair · gpt-3.5-turbo

    references to the petroleum industry and related concepts

    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
     Grimm
    -0.79
     Hancock
    -0.78
     Cardinal
    -0.78
     CLSID
    -0.76
    shaw
    -0.75
     Sparrow
    -0.74
    uders
    -0.73
     Bear
    -0.70
     Schne
    -0.69
    oldemort
    -0.68
    POSITIVE LOGITS
    roleum
    1.19
     petroleum
    1.08
     refinery
    0.91
    utical
    0.89
     Petroleum
    0.87
     fumes
    0.87
     lubric
    0.86
     oil
    0.85
    anol
    0.85
     jelly
    0.82
    Activations Density 0.014%

    No Known Activations