© 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. 1576
    Prev
    Next
    INDEX
    Explanations

    references to the movie franchise "Fast and Furious"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Fast and Furious" 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
     Seym
    -1.07
    xual
    -1.03
    ktop
    -0.87
    eryl
    -0.82
    aution
    -0.78
    cules
    -0.75
     ç¥ŀ
    -0.75
    pheus
    -0.72
    hovah
    -0.71
    mble
    -0.71
    POSITIVE LOGITS
    fast
    0.99
    idious
    0.99
    lane
    0.99
     paced
    0.87
    Fast
    0.86
    estone
    0.84
    Forward
    0.81
    itude
    0.81
    ener
    0.81
     Fast
    0.81
    Activations Density 0.008%

    No Known Activations