© 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. 11-RES-JB
    11. 9247
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or entities, specifically those containing "ek"

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns or mentions, particularly names or identifiers that begin with "ek."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AMERICA
    -0.72
     hitters
    -0.64
     buffet
    -0.62
    ÙĴ
    -0.62
     domestically
    -0.61
     Bland
    -0.61
     downhill
    -0.59
     vested
    -0.57
     gymn
    -0.57
     wrestlers
    -0.56
    POSITIVE LOGITS
    nown
    1.66
    yll
    1.22
    hov
    1.14
    enstein
    1.10
    ker
    1.05
    ko
    1.02
    tu
    1.01
    anism
    1.00
    tion
    0.98
    kers
    0.98
    Activations Density 0.037%

    No Known Activations