© 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. 9-RES-JB
    11. 9876
    Prev
    Next
    INDEX
    Explanations

    references to the movie "The Dark Knight Rises"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Dark" franchise, including its titles and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duly
    -0.77
    ractive
    -0.68
    PROV
    -0.68
     includ
    -0.67
    INS
    -0.67
    PsyNetMessage
    -0.67
    kson
    -0.66
    uated
    -0.66
     autop
    -0.66
     AAP
    -0.65
    POSITIVE LOGITS
     Ages
    1.07
     Horse
    1.06
    moon
    0.91
     Horses
    0.88
     Passenger
    0.86
    lance
    0.84
     Matter
    0.84
     Horizons
    0.83
     Knight
    0.82
     Souls
    0.81
    Activations Density 0.029%

    No Known Activations