© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1178
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "Von"

    oai_token-act-pair · gpt-3.5-turbo

    the name or variations of the name "Von" and its occurrences in the text

    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
     cleansing
    -0.71
     Caribbean
    -0.68
    SEA
    -0.68
     scrub
    -0.68
     freshwater
    -0.68
     irrig
    -0.67
     Swansea
    -0.66
     canoe
    -0.66
     flood
    -0.66
     Indigenous
    -0.65
    POSITIVE LOGITS
     Von
    3.56
     von
    3.31
    von
    1.95
     Vander
    1.64
     Wilhelm
    1.35
     Schwarz
    1.30
     Friedrich
    1.25
     Werner
    1.21
     Zimmer
    1.20
     Niet
    1.11
    Activations Density 0.026%

    No Known Activations