© 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 EvalsExportsinterp-engineNEWAPI 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. 18849
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts of interest

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases related to "conflict of interest."

    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
    LESS
    -0.79
     Die
    -0.70
    Die
    -0.68
     Indigo
    -0.66
     Rise
    -0.63
     perish
    -0.62
     Trash
    -0.62
     Dodge
    -0.59
    Drag
    -0.59
     Unch
    -0.59
    POSITIVE LOGITS
     interest
    1.14
     interests
    1.09
    interest
    0.92
     Interest
    0.92
     conscience
    0.78
     tradem
    0.76
    rontal
    0.75
     faith
    0.75
    iliation
    0.70
     counsel
    0.69
    Activations Density 0.045%

    No Known Activations