© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3216
    Prev
    Next
    INDEX
    Explanations

    references to movie titles and specific events within a film series

    oai_token-act-pair · gpt-3.5-turbo

    titles and references related to movies or series in the "Age of" and "Dawn of" series

    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
     mush
    -0.68
     ABE
    -0.64
     Huff
    -0.61
     serotonin
    -0.61
    heet
    -0.61
     paddle
    -0.61
     canoe
    -0.59
     HRC
    -0.59
    aminer
    -0.59
     toler
    -0.59
    POSITIVE LOGITS
    bringer
    1.30
     Of
    1.26
     Reborn
    1.14
    breaker
    1.10
    Of
    1.08
    blade
    1.05
    hunter
    1.03
    lords
    0.95
     Trilogy
    0.95
     of
    0.92
    Activations Density 0.160%

    No Known Activations