© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 6148
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mu"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Mulder" in various contexts, likely referring to a specific character or individual in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORED
    -0.83
    itals
    -0.74
    rolet
    -0.71
    CLOSE
    -0.71
     Hatch
    -0.68
    ECA
    -0.67
    ital
    -0.66
     Indianapolis
    -0.66
    ored
    -0.65
    ecake
    -0.65
    POSITIVE LOGITS
     Mu
    3.88
    Mu
    2.84
     mu
    2.24
     Scully
    1.64
     MU
    1.62
    mu
    1.57
     Muhammad
    1.49
     Mo
    1.17
     Maul
    1.16
    MU
    1.16
    Activations Density 0.012%

    No Known Activations