© 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 EvalsExportsAPI 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. 6-RES-JB
    11. 17726
    Prev
    Next
    INDEX
    Explanations

    words related to unethical or illegal behavior, specifically misconduct

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "misconduct" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LM
    -0.76
    hered
    -0.73
     Sabha
    -0.69
     Lear
    -0.68
    ebus
    -0.68
    zan
    -0.66
    izen
    -0.64
     Collider
    -0.63
    oos
    -0.63
     Juliet
    -0.63
    POSITIVE LOGITS
    owship
    0.99
     discharge
    0.76
    utes
    0.73
    onduct
    0.71
    uracy
    0.69
     misconduct
    0.69
    aunders
    0.68
    orem
    0.66
    eatures
    0.66
    misc
    0.66
    Activations Density 0.037%

    No Known Activations