© 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. 1-RES-JB
    11. 6406
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'proper'

    oai_token-act-pair · gpt-3.5-turbo

    the word "proper" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amon
    -0.81
     Abdel
    -0.74
    =-=-=-=-=-=-=-=-
    -0.69
    =-=-=-=-
    -0.67
     Von
    -0.65
    dust
    -0.63
    peak
    -0.63
     Hoffman
    -0.63
    ---------
    -0.63
    ranging
    -0.63
    POSITIVE LOGITS
    tarian
    1.04
     proper
    0.95
     etiquette
    0.90
     actionGroup
    0.84
    tarians
    0.83
     disposal
    0.81
     upkeep
    0.80
     nomine
    0.80
    eln
    0.78
     manners
    0.78
    Activations Density 0.006%

    No Known Activations