© 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. 2-RES-JB
    11. 5689
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Drake"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Drake" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.73
    urgical
    -0.71
    erala
    -0.70
     MSI
    -0.67
    ounding
    -0.65
    ative
    -0.65
    uilding
    -0.65
    hemat
    -0.65
    olitan
    -0.64
     Mandal
    -0.64
    POSITIVE LOGITS
     Drake
    1.36
    weed
    0.93
    knife
    0.84
    berry
    0.82
    ham
    0.82
    dra
    0.81
     Passage
    0.81
    brush
    0.78
    pool
    0.77
    butt
    0.76
    Activations Density 0.006%

    No Known Activations