© 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. 1-RES-JB
    11. 24050
    Prev
    Next
    INDEX
    Explanations

    phrases involving glyph variations of the Greek letter "Î"

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "Î" in various contexts, possibly relating to mathematical or statistical functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mph
    -0.87
    ned
    -0.84
    ning
    -0.82
    awan
    -0.82
    EEE
    -0.80
    hander
    -0.79
    istry
    -0.77
    ners
    -0.77
    nery
    -0.77
    luent
    -0.75
    POSITIVE LOGITS
     Amph
    0.73
     adaptive
    0.67
     Scand
    0.66
     retracted
    0.66
     Tob
    0.66
     Î
    0.65
     Austral
    0.64
     pept
    0.64
     Pact
    0.63
     landsl
    0.63
    Activations Density 0.024%

    No Known Activations