© 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. 10-RES-JB
    11. 2247
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Star Wars."

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Star Wars" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.81
    terday
    -0.73
    ecause
    -0.73
     LIA
    -0.72
    udeau
    -0.70
    utics
    -0.69
    eger
    -0.69
    éĹĺ
    -0.68
    ipop
    -0.68
    essee
    -0.67
    POSITIVE LOGITS
     Trek
    1.25
    vation
    1.24
     Wars
    1.24
    Wars
    1.10
    burst
    1.08
    light
    1.08
    bucks
    1.07
    fish
    1.05
    buck
    1.04
    ving
    1.03
    Activations Density 0.031%

    No Known Activations