© 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. 0-RES-JB
    11. 19091
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "baum" at varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Baum."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     const
    -0.69
     fishing
    -0.66
     pride
    -0.64
     ang
    -0.59
     Hep
    -0.59
     GST
    -0.58
     scene
    -0.58
     UT
    -0.57
     Capt
    -0.56
     suffering
    -0.56
    POSITIVE LOGITS
    baum
    4.95
    wald
    1.49
    schild
    1.41
    bach
    1.39
    witz
    1.35
    berger
    1.30
    baugh
    1.25
    heit
    1.23
    fman
    1.22
    feld
    1.22
    Activations Density 0.019%

    No Known Activations