© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2293
    Prev
    Next
    INDEX
    Explanations

    instances of lying or deception in sentences

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    instances of dishonesty or deception

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ugal
    -0.70
    ione
    -0.65
     Palo
    -0.64
     Alto
    -0.62
    JV
    -0.62
     STL
    -0.62
     Rivals
    -0.61
    iances
    -0.61
     Flavoring
    -0.60
    ynski
    -0.59
    POSITIVE LOGITS
    uten
    1.22
     detector
    1.16
     awake
    1.02
     about
    1.00
    about
    0.96
     ABOUT
    0.87
     dormant
    0.86
     detectors
    0.85
    utenant
    0.84
     cheat
    0.77
    Activations Density 0.044%

    No Known Activations