© 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. 8-RES-JB
    11. 7898
    Prev
    Next
    INDEX
    Explanations

    requests for information or tips on investigations or troubleshooting

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to requests for information or tips in a law enforcement context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utical
    -0.65
    Average
    -0.62
     resemb
    -0.61
     ax
    -0.59
    loads
    -0.59
     decaying
    -0.58
    é£
    -0.58
     sust
    -0.57
    Appearance
    -0.57
    æѦ
    -0.56
    POSITIVE LOGITS
    Email
    1.04
     Contact
    1.01
     contact
    0.98
     forwarded
    0.96
    mail
    0.94
     Email
    0.93
     email
    0.92
     emailed
    0.92
     answ
    0.87
    contact
    0.84
    Activations Density 0.167%

    No Known Activations