© 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. 3-RES-JB
    11. 6260
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrities or sports figures being drafted into professional teams or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "drafted."

    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
    eda
    -0.78
    esa
    -0.71
    piece
    -0.70
    ofi
    -0.70
    plug
    -0.69
    nen
    -0.67
    til
    -0.66
    wig
    -0.66
    boats
    -0.66
    fleet
    -0.66
    POSITIVE LOGITS
    entious
    0.91
     drafted
    0.85
     drafting
    0.82
    GGGGGGGG
    0.76
    ãĥ³ãĤ¸
    0.75
     practition
    0.75
    ãĥį
    0.72
    otype
    0.72
    untarily
    0.71
     unintention
    0.71
    Activations Density 0.013%

    No Known Activations