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. 18742
    Prev
    Next
    INDEX
    Explanations

    words that imply acceptance, approval, or greeting

    oai_token-act-pair · gpt-3.5-turbo

    expressions of acceptance or approval

    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
    negie
    -0.87
    uyomi
    -0.82
    agnetic
    -0.78
    aunder
    -0.77
    vertisement
    -0.77
    iph
    -0.72
    chn
    -0.71
    arcity
    -0.70
    amation
    -0.70
    ixtape
    -0.69
    POSITIVE LOGITS
     laughter
    0.84
     visitors
    0.82
     newcomers
    0.77
    ansen
    0.75
     arrivals
    0.71
     welcomes
    0.71
    ï¸
    0.71
     aboard
    0.70
     guests
    0.70
     Nikki
    0.70
    Activations Density 0.015%

    No Known Activations