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. 3-RES-JB
    6. 18823
    Prev
    Next
    INDEX
    Explanations

    the word "Happy"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Happy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDER
    -0.87
    arin
    -0.87
    urally
    -0.86
    ents
    -0.82
    ental
    -0.77
    andestine
    -0.76
    ently
    -0.74
    encers
    -0.72
    encies
    -0.72
     Ernst
    -0.72
    POSITIVE LOGITS
     Happy
    0.96
    Happy
    0.91
     Birthday
    0.91
    joy
    0.84
     Meal
    0.83
     happy
    0.81
    ness
    0.81
    happy
    0.81
     birthday
    0.78
     Joy
    0.72
    Activations Density 0.012%

    No Known Activations