© 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. 24238
    Prev
    Next
    INDEX
    Explanations

    references to the letters 'Ey'

    oai_token-act-pair · gpt-3.5-turbo

    the word "Ey" appearing multiple times in 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
    icum
    -0.78
    tumblr
    -0.71
    ional
    -0.69
    ãģª
    -0.66
     congr
    -0.66
    FORM
    -0.65
    士
    -0.65
     containment
    -0.63
    ãģĤ
    -0.63
    henko
    -0.62
    POSITIVE LOGITS
    ewitness
    1.42
    Ey
    1.02
     Ey
    1.01
    gments
    0.95
    eworks
    0.92
    vind
    0.88
    ogly
    0.85
    ldom
    0.80
    ight
    0.79
    azz
    0.79
    Activations Density 0.008%

    No Known Activations