© 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. 22478
    Prev
    Next
    INDEX
    Explanations

    proper nouns that start with the letter "Z"

    oai_token-act-pair · gpt-3.5-turbo

    names or references to individuals or entities, particularly those starting with "Z" or containing similar patterns

    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
     prank
    -0.71
     unheard
    -0.61
     antid
    -0.60
     intimidating
    -0.60
     eaves
    -0.60
     faint
    -0.58
     phantom
    -0.58
     humble
    -0.58
     pun
    -0.58
    ADVERTISEMENT
    -0.57
    POSITIVE LOGITS
    chini
    0.90
    zag
    0.88
    abwe
    0.87
    urgy
    0.84
    axies
    0.84
    heng
    0.80
    otti
    0.78
    ĪĴ
    0.78
    illi
    0.77
    ewski
    0.77
    Activations Density 0.118%

    No Known Activations