© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 17281
    Prev
    Next
    INDEX
    Explanations

    mentions of illegal drugs and medical terms related to drugs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illegal drugs and substance abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bird
    -0.83
     srfAttach
    -0.81
     Franchise
    -0.80
    LCS
    -0.77
    egal
    -0.73
    Pie
    -0.73
     UNESCO
    -0.69
    Panel
    -0.68
    equality
    -0.68
     Railway
    -0.67
    POSITIVE LOGITS
     pills
    1.62
     fentanyl
    1.56
     morphine
    1.54
     narc
    1.53
     overdose
    1.53
     dosage
    1.52
     ecstasy
    1.51
     MDMA
    1.51
    entanyl
    1.50
     methamphetamine
    1.49
    Activations Density 0.615%

    No Known Activations