© 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. 2-RES-JB
    11. 12216
    Prev
    Next
    INDEX
    Explanations

    phrases containing the letter combination "mu" and names like "McGee."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific unit of measurement or scientific notation related to mu

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
     Overse
    -0.68
     Pirates
    -0.67
    breaks
    -0.66
     UID
    -0.66
     Cavaliers
    -0.65
     Icelandic
    -0.65
     Pagan
    -0.63
     Dayton
    -0.63
     Beyond
    -0.62
    POSITIVE LOGITS
    hammad
    1.25
    berman
    0.99
    udge
    0.94
    mu
    0.87
    gee
    0.86
    cca
    0.86
    selage
    0.84
    htar
    0.81
    clair
    0.81
    phis
    0.80
    Activations Density 0.008%

    No Known Activations