© 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. 3-RES-JB
    11. 4824
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the "Guardians of the Galaxy" franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Guardians of the Galaxy" 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
    ffe
    -0.82
    enegger
    -0.81
    ebin
    -0.74
    ©¶æ
    -0.70
    rien
    -0.70
    med
    -0.68
    urses
    -0.67
    pled
    -0.66
    mington
    -0.66
    cles
    -0.65
    POSITIVE LOGITS
    hip
    1.13
    hips
    1.10
     Guardians
    1.05
    arium
    0.84
    naire
    0.81
    auts
    0.78
     guardians
    0.78
     Crusade
    0.78
    busters
    0.75
     Voices
    0.75
    Activations Density 0.011%

    No Known Activations