© 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. 6-RES-JB
    11. 12807
    Prev
    Next
    INDEX
    Explanations

    words related to drug overdose and crisis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "overdose" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hip
    -0.81
    ois
    -0.77
    mouth
    -0.74
     Ard
    -0.69
    auga
    -0.67
    hips
    -0.67
    berman
    -0.67
    ument
    -0.66
    ozy
    -0.65
     Pug
    -0.65
    POSITIVE LOGITS
    ridden
    0.82
    uler
    0.74
    uly
    0.74
    ulously
    0.73
    lich
    0.70
    ENE
    0.68
    icum
    0.68
    MW
    0.67
    ussions
    0.67
    ãĤ¼ãĤ¦ãĤ¹
    0.67
    Activations Density 0.084%

    No Known Activations