© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    references to the term "Star Wars."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 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 @ 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
    onym
    -0.81
    itute
    -0.76
    ickr
    -0.74
    OGR
    -0.70
    Reviewer
    -0.68
    onyms
    -0.68
    METHOD
    -0.67
    umbn
    -0.67
    orative
    -0.67
    SPONSORED
    -0.66
    POSITIVE LOGITS
     Kenobi
    1.08
     Awakens
    1.04
     Wars
    0.97
     Skywalker
    0.91
    fare
    0.86
     Rebels
    0.85
     trilogy
    0.84
    âĦ¢:
    0.83
     ®
    0.81
     Odyssey
    0.81
    Activations Density 0.017%

    No Known Activations