© 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. 9-RES-JB
    11. 1987
    Prev
    Next
    INDEX
    Explanations

    mentions of the Koch brothers

    oai_token-act-pair · gpt-3.5-turbo

    references to the Koch brothers and their associated organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alling
    -0.83
    alled
    -0.70
    ths
    -0.68
    hani
    -0.65
    keeping
    -0.64
    ournal
    -0.63
    yll
    -0.63
    resses
    -0.61
    alty
    -0.61
     Overwatch
    -0.61
    POSITIVE LOGITS
    anski
    0.87
     Industries
    0.81
     Koch
    0.77
    liga
    0.76
    Mos
    0.75
    ileaks
    0.75
    milo
    0.74
    ifer
    0.71
     Brothers
    0.71
    FFFF
    0.69
    Activations Density 0.090%

    No Known Activations