© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7003
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Till" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Till" and variations of the word "til."

    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
    TABLE
    -0.92
    VERTISEMENT
    -0.75
    ItemImage
    -0.72
    Table
    -0.70
    Loading
    -0.69
    BOOK
    -0.68
    Es
    -0.67
     Revolutionary
    -0.66
    Common
    -0.65
    ä
    -0.65
    POSITIVE LOGITS
    helm
    0.84
    iman
    0.80
    ting
    0.79
    burg
    0.78
    sten
    0.78
     Til
    0.78
    alde
    0.75
    obos
    0.74
    ogram
    0.74
    ted
    0.74
    Activations Density 0.008%

    No Known Activations