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. 22416
    Prev
    Next
    INDEX
    Explanations

    questions asking about quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    questions related to quantities or measurements concerning money and economics

    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
    teness
    -0.81
    bent
    -0.76
    ody
    -0.67
     Cosponsors
    -0.64
     Hels
    -0.64
     Calm
    -0.63
    RAW
    -0.62
     Families
    -0.62
    ivot
    -0.61
     Delicious
    -0.60
    POSITIVE LOGITS
     actually
    0.74
     realistically
    0.72
    /$
    0.71
    actually
    0.65
     individually
    0.63
     depends
    0.63
     sausage
    0.63
     depend
    0.62
     clitor
    0.60
     dred
    0.60
    Activations Density 0.214%

    No Known Activations