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. 20589
    Prev
    Next
    INDEX
    Explanations

    expressions related to greetings or well-wishes, specifically the phrase "Happy" followed by a specific occasion or sentiment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of happiness, particularly in the context of celebrations and greetings

    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
    iban
    -0.78
    urally
    -0.77
    soDeliveryDate
    -0.77
    arin
    -0.75
    DoS
    -0.74
    ngth
    -0.74
    Rush
    -0.72
    rovers
    -0.68
    ilian
    -0.68
    heed
    -0.67
    POSITIVE LOGITS
     birthday
    0.92
     Birthday
    0.87
     endings
    0.83
     Meal
    0.79
    istic
    0.77
    vale
    0.71
     Mondays
    0.69
    ãĥĸ
    0.69
     Gilmore
    0.69
    joy
    0.68
    Activations Density 0.049%

    No Known Activations