© 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. 0-RES-JB
    11. 13348
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Mus" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Mus" followed by various contexts, likely indicating a focus on musical topics or references related to musicians

    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
     CE
    -0.76
     disinfect
    -0.75
    ENT
    -0.71
    ETA
    -0.68
     prepaid
    -0.68
     vaping
    -0.66
     deductible
    -0.66
    duty
    -0.65
     goodbye
    -0.65
     override
    -0.65
    POSITIVE LOGITS
     Mus
    3.91
    Mus
    2.92
     mus
    1.90
     MUS
    1.76
    mus
    1.71
     Muscle
    1.41
     Muse
    1.38
     Musical
    1.29
     Musk
    1.22
     Mous
    1.20
    Activations Density 0.009%

    No Known Activations