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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14404
    Prev
    Next
    INDEX
    Explanations

    words related to emotional states of happiness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 5 - happiness

    No Comments

    Negative Logits
    ngth
    -0.80
    soDeliveryDate
    -0.79
    DoS
    -0.77
    ciplinary
    -0.76
    BOOK
    -0.72
    Downloadha
    -0.71
    çīĪ
    -0.70
    authorized
    -0.70
    OLOGY
    -0.69
    zan
    -0.68
    POSITIVE LOGITS
    joy
    0.86
    vale
    0.84
    istic
    0.74
     Meal
    0.71
     âĶľ
    0.70
     happily
    0.70
     birthday
    0.70
     happy
    0.68
     endings
    0.65
     Onion
    0.65
    Activations Density 0.022%

    No Known Activations