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

    Neuronpedia

    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. 9470
    Prev
    Next
    INDEX
    Explanations

    words related to individuals named "Kowalski"

    oai_token-act-pair · gpt-3.5-turbo

    the word "ow" and its variations, indicating a focus on a specific phrase or expression of acknowledgment

    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
     infiltrate
    -0.76
    senal
    -0.73
    £ı
    -0.71
     seiz
    -0.68
     locality
    -0.68
    ually
    -0.67
    xon
    -0.66
     suspic
    -0.65
     latex
    -0.65
    ĸļ
    -0.65
    POSITIVE LOGITS
    orld
    1.16
    atche
    1.09
    ards
    1.05
    olves
    1.05
    atts
    1.01
    idth
    1.01
    een
    0.99
    ells
    0.97
    restling
    0.95
    aways
    0.94
    Activations Density 0.015%

    No Known Activations