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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27061
    Prev
    Next
    INDEX
    Explanations

    references to age, specifically focusing on older individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    362
    +0.15
    0.8%
    156
    +0.14
    0.7%
    128
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.03
    128
    +0.14
    0.02
    1
    +0.12
    0.02
    Negative Logits
    lest
    -1.73
    ights
    -1.73
    async
    -1.57
    alysis
    -1.53
    ycl
    -1.49
    tte
    -1.46
    esan
    -1.46
    oof
    -1.45
    asek
    -1.45
    ount
    -1.41
    POSITIVE LOGITS
     than
    2.60
     generations
    2.18
    Than
    2.13
     Than
    2.04
     versions
    1.93
     generation
    1.88
    than
    1.76
     adulthood
    1.67
     version
    1.60
     (âī¥
    1.59
    Activations Density 0.056%

    No Known Activations