© 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. 18971
    Prev
    Next
    INDEX
    Explanations

    phrases related to being caught in a negative or incriminating situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "caught"

    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
    issance
    -0.65
    study
    -0.65
    ukong
    -0.64
    guided
    -0.64
    olas
    -0.64
    VERTISEMENT
    -0.61
    enthal
    -0.61
     ceremonies
    -0.61
    profits
    -0.60
    urai
    -0.59
    POSITIVE LOGITS
     unprepared
    1.13
     cheating
    0.91
     plagiar
    0.91
     stealing
    0.91
     tampering
    0.90
     unaware
    0.90
     violating
    0.75
     sneaking
    0.74
    gling
    0.74
     dere
    0.74
    Activations Density 0.026%

    No Known Activations