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. 8-RES-JB
    6. 16073
    Prev
    Next
    INDEX
    Explanations

    age-related information, such as the age of individuals in news articles or stories

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prometheus
    -0.65
     Rocky
    -0.65
     Proc
    -0.63
     Twain
    -0.63
     Zoro
    -0.59
     Rossi
    -0.59
     gum
    -0.59
     Cassidy
    -0.59
     bri
    -0.59
     Narc
    -0.58
    POSITIVE LOGITS
    year
    1.34
    degree
    1.27
    minute
    1.21
    hour
    1.15
    member
    1.12
    percent
    1.11
    page
    1.10
    strong
    1.09
    acre
    1.07
    month
    1.06
    Activations Density 0.074%

    No Known Activations