© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    instances of the word "drag" followed by a number indicating the strength of the association

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "drag" in different contexts

    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
    cium
    -0.78
     Nest
    -0.77
    etts
    -0.73
     Kell
    -0.67
    arium
    -0.64
     Pere
    -0.63
    ettlement
    -0.63
     Iw
    -0.63
    Oracle
    -0.62
     Mah
    -0.62
    POSITIVE LOGITS
     drag
    4.15
     Drag
    2.74
    Drag
    2.61
     dragging
    2.02
     DRAG
    1.90
     dragged
    1.76
     dr
    1.05
     tug
    1.03
     drift
    1.03
     queens
    1.03
    Activations Density 0.007%

    No Known Activations