© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 2962
    Prev
    Next
    INDEX
    Explanations

    phrases related to accusations of misconduct or dishonesty

    oai_token-act-pair · gpt-3.5-turbo

    instances of corruption and malpractice in various contexts

    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
    aphael
    -0.81
     Veg
    -0.77
     flavours
    -0.75
    ãĥĪ
    -0.75
    ottenham
    -0.73
     Wim
    -0.73
    jab
    -0.73
     Waves
    -0.73
    ipeg
    -0.72
    ãĤª
    -0.72
    POSITIVE LOGITS
     misconduct
    1.66
     violations
    1.56
     malf
    1.46
     wrongdoing
    1.42
     egregious
    1.37
     scandals
    1.35
     audits
    1.35
     improper
    1.33
     incompetence
    1.32
     systemic
    1.30
    Activations Density 1.048%

    No Known Activations