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. 6747
    Prev
    Next
    INDEX
    Explanations

    keywords related to emotional well-being and positive feelings

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to happiness and well-being

    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
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.81
    MpServer
    -0.77
    enegger
    -0.71
    soDeliveryDate
    -0.70
    DoS
    -0.70
     Cosponsors
    -0.70
    heny
    -0.69
     CFR
    -0.67
     Runner
    -0.65
     Shinra
    -0.64
    POSITIVE LOGITS
    fulness
    0.84
    ful
    0.82
    idays
    0.79
     happiness
    0.78
     expectancy
    0.77
    appiness
    0.75
    ternity
    0.74
    aviour
    0.73
     wellbeing
    0.73
    istic
    0.72
    Activations Density 0.019%

    No Known Activations