© 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. 23763
    Prev
    Next
    INDEX
    Explanations

    terms related to the ExxonMobil company and its activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the ExxonMobil corporation

    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
    HCR
    -0.82
    Interstitial
    -0.77
    tumblr
    -0.76
    ttp
    -0.76
    LOAD
    -0.72
    enance
    -0.68
    onsense
    -0.64
    WARE
    -0.63
    cgi
    -0.63
    req
    -0.61
    POSITIVE LOGITS
    Mobil
    1.62
     Mobil
    1.29
    xon
    1.13
     Vald
    0.95
    Cola
    0.93
     Exxon
    0.93
    ileaks
    0.83
    regate
    0.81
     gallon
    0.79
    esis
    0.78
    Activations Density 0.005%

    No Known Activations