Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 737
    Prev
    Next
    INDEX
    Explanations

    adjectives related to behavior or attitude towards others

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with rudeness and politeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARK
    -0.86
    lisher
    -0.83
    Downloadha
    -0.76
    assets
    -0.74
    uilding
    -0.73
    ernels
    -0.73
    MH
    -0.72
    lamm
    -0.71
    mental
    -0.70
    orama
    -0.68
    POSITIVE LOGITS
     banter
    1.00
     etiquette
    0.99
     manners
    0.98
     polite
    0.96
     politely
    0.91
     rude
    0.90
     demeanor
    0.88
     greeting
    0.87
    iquette
    0.85
     gentlemen
    0.81
    Activations Density 0.052%

    No Known Activations