Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3864
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Fentanyl"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the drug "Fentanyl" and its implications

    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
    colo
    -0.82
     Frieza
    -0.72
     Harbor
    -0.71
     Saiyan
    -0.70
     Cove
    -0.68
    Brave
    -0.66
     pardon
    -0.66
     Decker
    -0.65
     Tyson
    -0.65
    coin
    -0.64
    POSITIVE LOGITS
    yll
    1.95
    onal
    1.51
     Claus
    1.51
     Kath
    1.50
     Nad
    1.44
    yss
    1.30
     Berg
    1.27
     Sud
    1.26
     Lars
    1.22
     Patt
    1.20
    Activations Density 0.064%

    No Known Activations