© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 24310
    Prev
    Next
    INDEX
    Explanations

    information related to law enforcement efforts, drug trafficking, and criminal organizations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to law enforcement and drug trafficking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hawking
    -0.90
     Sturgeon
    -0.80
    ascript
    -0.76
    ecided
    -0.75
     Einstein
    -0.75
     Kerr
    -0.74
    è£ħ
    -0.74
    rompt
    -0.74
     Physics
    -0.73
    Phys
    -0.73
    POSITIVE LOGITS
     traffickers
    1.99
     trafficking
    1.90
     smuggling
    1.83
     traff
    1.74
     Traff
    1.66
     smugglers
    1.64
     narcotics
    1.62
     prostitution
    1.61
     illicit
    1.60
     gangs
    1.58
    Activations Density 0.934%

    No Known Activations