© 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. 11-RES-JB
    11. 11395
    Prev
    Next
    INDEX
    Explanations

    mentions of whistleblowers and actions related to whistleblowing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to whistleblowing and related acts of exposing wrongdoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itates
    -0.95
    itated
    -0.93
    itate
    -0.88
    itating
    -0.82
    icular
    -0.79
    anian
    -0.75
    usa
    -0.73
    izable
    -0.70
    hetical
    -0.66
    imus
    -0.65
    POSITIVE LOGITS
     whistle
    1.03
    oshenko
    0.88
     blowing
    0.86
     informant
    0.85
    dropping
    0.83
    bley
    0.79
     whistleblower
    0.78
    stakes
    0.78
     leak
    0.78
     secrecy
    0.77
    Activations Density 0.132%

    No Known Activations