© 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. 6152
    Prev
    Next
    INDEX
    Explanations

    phrases related to deception and dishonesty

    oai_token-act-pair · gpt-3.5-turbo

    instances of deception or misleading behavior in various contexts

    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
    anian
    -0.76
    erenn
    -0.72
    âĶģ
    -0.72
    furt
    -0.71
    interrupted
    -0.68
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.68
    noon
    -0.67
    reciation
    -0.67
    iannopoulos
    -0.66
    idian
    -0.65
    POSITIVE LOGITS
     witnesses
    0.87
     gull
    0.84
     facts
    0.81
     testimony
    0.78
     information
    0.77
     oath
    0.77
     evidence
    0.76
     taxpayers
    0.75
     disclosure
    0.75
     witness
    0.74
    Activations Density 0.231%

    No Known Activations