© 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. 6-RES-JB
    11. 5543
    Prev
    Next
    INDEX
    Explanations

    keywords related to corruption

    oai_token-act-pair · gpt-3.5-turbo

    references to corruption and related unethical practices

    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
    nee
    -0.81
    leigh
    -0.80
    imus
    -0.77
    thur
    -0.73
    mare
    -0.72
    ¯¯¯¯
    -0.72
    AY
    -0.71
    ofi
    -0.69
    yll
    -0.69
    lee
    -0.68
    POSITIVE LOGITS
     scandals
    0.98
     corruption
    0.93
     dealings
    0.84
     perpetrated
    0.81
     schemes
    0.79
     disproportion
    0.79
     corrupt
    0.78
     endemic
    0.77
     graft
    0.76
     scandal
    0.75
    Activations Density 0.025%

    No Known Activations