© 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. 8921
    Prev
    Next
    INDEX
    Explanations

    mentions of the drug "heroin."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and discussions about heroin and its effects

    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
    -0.77
    oÄŁ
    -0.75
    elong
    -0.75
    parts
    -0.74
     Democr
    -0.73
    semble
    -0.73
    rons
    -0.72
    din
    -0.70
    nant
    -0.69
    eor
    -0.68
    POSITIVE LOGITS
     heroin
    1.11
     overdoses
    1.03
     addiction
    1.01
     overdose
    0.97
     addict
    0.97
     addicts
    0.88
     cocaine
    0.82
     fentanyl
    0.81
     poppy
    0.80
     opium
    0.80
    Activations Density 0.006%

    No Known Activations