© 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. 4-RES-JB
    11. 10200
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with the word "Mu" followed by varying characters

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mu" and its various contexts

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

    No Comments

    Negative Logits
    姫
    -0.77
     wip
    -0.75
    */(
    -0.70
     UID
    -0.67
     SPACE
    -0.65
     Eleven
    -0.65
     BART
    -0.65
     Cosponsors
    -0.64
     CBI
    -0.63
    ECT
    -0.63
    POSITIVE LOGITS
    lder
    1.10
    hammad
    1.04
    zik
    1.02
    udge
    1.01
    osh
    0.98
    gee
    0.98
    ahah
    0.95
    selage
    0.94
     Klux
    0.92
    jer
    0.92
    Activations Density 0.004%

    No Known Activations