© 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. 3-RES-JB
    11. 15080
    Prev
    Next
    INDEX
    Explanations

    terms related to drugs, especially cocaine

    oai_token-act-pair · gpt-3.5-turbo

    references to cocaine and its related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.86
    hof
    -0.78
    EVA
    -0.75
    igating
    -0.74
    LOC
    -0.74
    Reviewer
    -0.74
    aer
    -0.73
     Arbor
    -0.72
    Bird
    -0.72
    DEM
    -0.70
    POSITIVE LOGITS
     cocaine
    1.26
     residue
    1.02
     addiction
    0.97
    stasy
    0.95
     addicts
    0.93
     methamphetamine
    0.92
     heroin
    0.91
     addict
    0.90
     overdose
    0.89
     cartel
    0.89
    Activations Density 0.007%

    No Known Activations