© 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. 8-RES-JB
    11. 22707
    Prev
    Next
    INDEX
    Explanations

    keywords related to drug use and addiction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drug use and addiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angular
    -0.82
     Parables
    -0.81
    Engineers
    -0.80
     Eag
    -0.78
     Layout
    -0.76
    Pie
    -0.76
    Pont
    -0.75
    Struct
    -0.74
    prise
    -0.72
     UNESCO
    -0.72
    POSITIVE LOGITS
     cocaine
    1.64
     methamphetamine
    1.56
     drugs
    1.55
     heroin
    1.41
    alcohol
    1.39
     drug
    1.36
     intoxication
    1.35
    amphetamine
    1.35
     alcohol
    1.34
     overdose
    1.33
    Activations Density 0.362%

    No Known Activations