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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 16716
    Prev
    Next
    INDEX
    Explanations

    mentions of corruption, unethical behavior, and legal charges related to corruption

    oai_token-act-pair · gpt-3.5-turbo

    references to corruption and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imus
    -0.75
    mare
    -0.75
    leigh
    -0.73
    nee
    -0.70
    AY
    -0.69
     Advent
    -0.66
    agen
    -0.66
    osphere
    -0.65
    lee
    -0.65
    answer
    -0.64
    POSITIVE LOGITS
     scandals
    0.95
     corruption
    0.90
     dealings
    0.88
     corrupt
    0.85
     graft
    0.82
     perpetrated
    0.81
     schemes
    0.80
    ulent
    0.77
     Corruption
    0.75
     allegations
    0.75
    Activations Density 0.042%

    No Known Activations