© 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. 10266
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Miguel"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Miguel."

    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
    Ħ¢
    -0.88
    ivity
    -0.79
    hip
    -0.79
    tops
    -0.76
    ĪĴ
    -0.75
    frames
    -0.74
    board
    -0.73
    perse
    -0.73
    SpaceEngineers
    -0.72
    rup
    -0.68
    POSITIVE LOGITS
     Cabrera
    0.91
    entanyl
    0.86
    insk
    0.78
    uez
    0.75
     Miguel
    0.75
    udeau
    0.75
    illo
    0.73
     Sturgeon
    0.71
    ixture
    0.70
     Chavez
    0.67
    Activations Density 0.015%

    No Known Activations