© 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. 2-RES-SM
    11. 10234
    Prev
    Next
    INDEX
    Explanations

    temporal expressions, specifically durations of time

    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
    91
    +0.13
    0.7%
    216
    +0.11
    0.6%
    253
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.13
    0.03
    364
    +0.11
    0.04
    297
    +0.11
    0.04
    Negative Logits
    ©
    -5.47
    ĨĴ
    -5.40
    ĻĤ
    -5.39
    ↵
    -5.33
         ↵
    -5.33
    <|outofrange|>
    -5.33
     ↵
    -5.33
    <|outofrange|>
    -5.33
    -5.33
      ↵
    -5.33
    POSITIVE LOGITS
     horizon
    1.70
    UMENT
    1.47
    iments
    1.45
    alth
    1.43
    velt
    1.41
    uppose
    1.40
    olve
    1.39
    ontal
    1.37
    deb
    1.35
    views
    1.35
    Activations Density 0.265%

    No Known Activations