© 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 EvalsExportsinterp-engineNEWAPI 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. 4-RES-JB
    11. 10043
    Prev
    Next
    INDEX
    Explanations

    phrases related to substance abuse, illegal drug use, and possession

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drug use and abuse

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

    No Comments

    Negative Logits
    Hug
    -0.83
    Bird
    -0.80
    Solar
    -0.79
    Temp
    -0.79
    AUT
    -0.76
    AIR
    -0.75
    Wind
    -0.74
    soType
    -0.72
    Arch
    -0.71
    WIND
    -0.70
    POSITIVE LOGITS
     methamphetamine
    1.20
     drugs
    1.18
     cocaine
    1.17
     overdose
    1.15
     addiction
    1.14
     overdoses
    1.08
     stimul
    1.08
     heroin
    1.05
    hetamine
    1.01
     substances
    1.01
    Activations Density 0.126%

    No Known Activations