© 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. 9-RES-JB
    11. 4166
    Prev
    Next
    INDEX
    Explanations

    references to actions related to dishonesty or rule-breaking, specifically cheating

    oai_token-act-pair · gpt-3.5-turbo

    references to cheating or dishonest behavior

    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
    eric
    -0.68
    nesota
    -0.68
    algia
    -0.67
    ä½ľ
    -0.67
    Vert
    -0.67
    00200000
    -0.66
    escal
    -0.64
    erick
    -0.64
     Archdemon
    -0.63
    esc
    -0.62
    POSITIVE LOGITS
     sheet
    0.86
     cheating
    0.84
     cheat
    0.83
    ulative
    0.79
    cheat
    0.69
     sheets
    0.69
    raud
    0.68
     cheated
    0.68
    sheet
    0.68
     Clever
    0.65
    Activations Density 0.050%

    No Known Activations