© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 11305
    Prev
    Next
    INDEX
    Explanations

    mentions of the drug "Fentanyl"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the drug "Phenethylamine."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gamb
    -0.66
     counters
    -0.64
     clutch
    -0.64
     Electronics
    -0.63
     JC
    -0.63
     mobile
    -0.62
     EV
    -0.62
     advanced
    -0.62
     Abyss
    -0.62
     tam
    -0.62
    POSITIVE LOGITS
    yll
    4.77
    ynt
    1.17
    leness
    1.08
    seys
    0.99
    yles
    0.98
    yt
    0.97
    yl
    0.96
    YL
    0.95
     unden
    0.94
    yne
    0.93
    Activations Density 0.029%

    No Known Activations