© 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. 11-RES-JB
    11. 20554
    Prev
    Next
    INDEX
    Explanations

    titles or references to the movie "Guardians of the Galaxy."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Guardians of the Galaxy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specials
    -0.73
    wcs
    -0.71
    Http
    -0.69
    nels
    -0.69
    redients
    -0.68
     showc
    -0.66
    tones
    -0.65
    gars
    -0.65
    Applications
    -0.65
    locks
    -0.64
    POSITIVE LOGITS
    fortune
    0.82
    rontal
    0.75
    iken
    0.74
     Paradise
    0.69
     Anarchy
    0.68
    opy
    0.68
     Liberty
    0.67
    ight
    0.67
     Galaxy
    0.66
     Coast
    0.65
    Activations Density 0.071%

    No Known Activations