© 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. 3004
    Prev
    Next
    INDEX
    Explanations

    specific terms related to movies, shows, and names, including titles like "Whispers of the Old Gods" and entities like "Disney Studios Japan."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific products, brands, or titles

    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
    govtrack
    -0.72
    Dispatch
    -0.72
     partName
    -0.67
    rawdownloadcloneembedreportprint
    -0.66
     Helpful
    -0.65
    gp
    -0.64
    erity
    -0.63
    borne
    -0.62
    mberg
    -0.61
    heast
    -0.59
    POSITIVE LOGITS
    âĸ¬
    0.66
    emale
    0.61
    vous
    0.61
    âĸ¬âĸ¬
    0.61
    ®
    0.58
    OHN
    0.57
    ucha
    0.55
    å½
    0.55
    λ
    0.55
    Weiss
    0.54
    Activations Density 0.166%

    No Known Activations