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. 26702
    Prev
    Next
    INDEX
    Explanations

    information related to environmental science and mathematical modeling

    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
    23
    +0.17
    1.0%
    458
    +0.12
    0.7%
    478
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.17
    0.04
    365
    +0.12
    0.08
    511
    +0.11
    0.06
    Negative Logits
    ĭ
    -1.92
    Ģ
    -1.84
    »¿
    -1.69
    į
    -1.68
    ĻĤ
    -1.66
     yards
    -1.65
    Ĭ
    -1.64
    %"
    -1.63
    ¼
    -1.62
    receptor
    -1.60
    POSITIVE LOGITS
     private
    1.55
     prophylactic
    1.46
     sincere
    1.42
    ))).
    1.41
     insights
    1.40
     suitable
    1.40
     minim
    1.39
     remed
    1.38
     ours
    1.37
     minimal
    1.35
    Activations Density 4.477%

    No Known Activations