© 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 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. 9-RES-JB
    11. 18310
    Prev
    Next
    INDEX
    Explanations

    terms related to crime and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to criminal activities and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agre
    -0.70
    ufact
    -0.58
     apiece
    -0.57
     Athletic
    -0.57
    assad
    -0.55
     challeng
    -0.55
    Congratulations
    -0.55
    aukee
    -0.54
     conclud
    -0.54
     refreshed
    -0.54
    POSITIVE LOGITS
     perpetrated
    0.99
     hoax
    0.97
     Illegal
    0.92
     malware
    0.90
     harming
    0.89
     criminals
    0.89
     scams
    0.88
     scam
    0.87
    criminal
    0.87
     crimes
    0.86
    Activations Density 1.162%

    No Known Activations