Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 8052
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveillance and monitoring for various purposes like security, law enforcement, and analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to identifying individuals or communities at risk or involved in certain behaviors or situations

    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
    ©¶æ¥µ
    -0.63
    wark
    -0.62
     WRITE
    -0.61
    ilogy
    -0.59
     welf
    -0.58
     Canter
    -0.57
     Blessing
    -0.56
    init
    -0.56
     Extended
    -0.56
    arist
    -0.55
    POSITIVE LOGITS
     suspicious
    0.89
     anomalies
    0.83
    ById
    0.80
     lurking
    0.78
     contaminants
    0.78
     missing
    0.76
     debris
    0.74
    usercontent
    0.72
     trespass
    0.72
    bugs
    0.72
    Activations Density 0.577%

    No Known Activations