© 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 EvalsExportsAPI 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. 10612
    Prev
    Next
    INDEX
    Explanations

    numbers or numerical values

    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
    156
    +0.28
    1.6%
    217
    +0.15
    0.9%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    456
    +0.28
    0.04
    410
    +0.15
    0.03
    34
    +0.14
    0.04
    Negative Logits
    ese
    -1.65
     aisle
    -1.59
    yles
    -1.51
     runway
    -1.50
     equity
    -1.49
    eston
    -1.48
    lique
    -1.47
     \[[
    -1.46
     fare
    -1.45
    ague
    -1.40
    POSITIVE LOGITS
    ¿½
    2.65
    ½
    2.60
    ĥ½
    2.51
    ŀ
    2.49
    ¼
    2.47
    ¤
    2.40
    ·¸
    2.36
    «
    2.30
    ´
    2.27
    Copyright
    2.25
    Activations Density 0.207%

    No Known Activations