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. 8-RES-JB
    6. 15451
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to greetings and welcoming others

    oai_token-act-pair · gpt-3.5-turbo

    instances of greetings or expressions of welcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulz
    -0.78
    negie
    -0.69
    uld
    -0.67
    gur
    -0.66
    ciplinary
    -0.64
    cano
    -0.64
    fighting
    -0.60
    unker
    -0.60
    âĵĺ
    -0.60
     inhibitor
    -0.60
    POSITIVE LOGITS
     greeting
    0.91
     greet
    0.90
     guests
    0.87
    enance
    0.85
     politely
    0.82
     passers
    0.80
    staff
    0.78
    ADRA
    0.78
     greeted
    0.77
    reetings
    0.76
    Activations Density 0.053%

    No Known Activations