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

    Neuronpedia

    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. 2-RES-SM
    11. 30039
    Prev
    Next
    INDEX
    Explanations

    dates and years in texts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    350
    +0.16
    0.9%
    203
    +0.13
    0.7%
    348
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.16
    0.04
    458
    +0.13
    0.03
    69
    +0.12
    0.04
    Negative Logits
    idious
    -1.56
    ying
    -1.54
     certain
    -1.46
    rends
    -1.46
     arms
    -1.41
     probing
    -1.40
     too
    -1.39
    ests
    -1.39
     nature
    -1.37
     familiar
    -1.35
    POSITIVE LOGITS
    ¦
    3.07
    ¾
    2.78
    ĥ½
    2.75
    ¨
    2.60
    ®
    2.38
    Ń
    2.35
    ¡
    2.32
    »
    2.22
    Ľ
    2.19
    ł
    2.19
    Activations Density 0.139%

    No Known Activations