© 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. 0-RES-JB
    11. 20046
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names containing the syllable "urt"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kurt" in various contexts

    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
     present
    -0.63
     staples
    -0.62
     service
    -0.61
     NFC
    -0.61
     governing
    -0.61
     polling
    -0.60
     extradition
    -0.59
     Cer
    -0.59
     fixing
    -0.59
     entry
    -0.59
    POSITIVE LOGITS
    urt
    4.57
    urs
    1.25
    urst
    1.17
    urat
    1.15
    ur
    1.14
    rug
    1.05
    urd
    1.04
    ait
    1.02
    irt
    0.99
    urb
    0.99
    Activations Density 0.012%

    No Known Activations