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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 12068
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific company "Oracle" and related terms like "Ellison" and "Bitrix"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company Oracle and its founder, Larry Ellison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matter
    -0.81
    irt
    -0.78
    irth
    -0.77
    mble
    -0.77
    fur
    -0.74
    ories
    -0.71
    rences
    -0.70
    eworld
    -0.69
    netflix
    -0.69
    erie
    -0.69
    POSITIVE LOGITS
     Oracle
    0.96
     Printed
    0.87
    ific
    0.75
    Oracle
    0.74
     Pharmaceutical
    0.70
    APH
    0.70
     STA
    0.70
     JD
    0.65
     membr
    0.65
     Arena
    0.65
    Activations Density 0.042%

    No Known Activations