© 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. 10-RES-JB
    11. 6252
    Prev
    Next
    INDEX
    Explanations

    words related to corporate activities and structures, such as "corporate," "shareholders," "business taxes," "bonuses," and "sponsorship."

    oai_token-act-pair · gpt-3.5-turbo

    references to corporate entities and their practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icans
    -0.76
    theless
    -0.75
    imental
    -0.74
    qi
    -0.73
    range
    -0.72
    uberty
    -0.71
    lessly
    -0.70
    qs
    -0.70
    shows
    -0.69
    mith
    -0.69
    POSITIVE LOGITS
     sponsorship
    1.04
     executives
    0.99
     restructuring
    0.93
    porate
    0.93
     espionage
    0.93
     governance
    0.93
     logos
    0.88
     profits
    0.87
     greed
    0.86
     sponsors
    0.86
    Activations Density 0.030%

    No Known Activations