© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 9563
    Prev
    Next
    INDEX
    Explanations

    financial terms and references related to fiscal periods

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    271
    +0.20
    1.1%
    306
    +0.12
    0.6%
    332
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.20
    0.03
    426
    +0.12
    0.02
    271
    +0.11
    0.01
    Negative Logits
     bells
    -1.96
    boarding
    -1.84
    doms
    -1.59
    falls
    -1.55
     await
    -1.51
    fully
    -1.50
    forms
    -1.49
    bag
    -1.48
    prises
    -1.46
     anonym
    -1.42
    POSITIVE LOGITS
    Ļª
    3.60
    Ĵ
    3.60
    ı
    3.52
    ij
    3.28
    ĥ
    3.24
    Ī
    3.07
    ĸ
    3.05
    ·¸
    3.04
    ´
    3.02
    ĨĴ
    2.99
    Activations Density 0.060%

    No Known Activations