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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6716
    Prev
    Next
    INDEX
    Explanations

    mentions of the movie "Guardians of the Galaxy."

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Guardians of the Galaxy."

    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
    wcs
    -0.85
    nels
    -0.79
    Http
    -0.75
    mson
    -0.72
     misdem
    -0.72
     spons
    -0.70
     vowel
    -0.70
    locks
    -0.69
    tons
    -0.68
     showc
    -0.67
    POSITIVE LOGITS
    fortune
    0.86
     Apocalypse
    0.83
     Anarchy
    0.78
    ©¶æ¥µ
    0.78
     Empire
    0.76
     Aether
    0.74
     Sunset
    0.74
     Galaxy
    0.73
     Liberty
    0.73
     paradise
    0.73
    Activations Density 0.050%

    No Known Activations