© 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. 1-RES-SM
    11. 25767
    Prev
    Next
    INDEX
    Explanations

    references to time-related phrases or the word "times."

    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
    77
    +0.15
    0.8%
    287
    +0.12
    0.7%
    471
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.15
    0.03
    471
    +0.12
    0.03
    287
    +0.12
    0.03
    Negative Logits
    Ħ
    -3.10
    ľĵ
    -3.10
    -3.09
    ↵
    -3.09
    -3.09
    ↵↵
    -3.09
    ↵
    -3.09
    -3.09
    -3.09
    ↵
    -3.09
    POSITIVE LOGITS
    pan
    2.46
    heet
    2.43
    heets
    2.38
    cale
    2.19
    creen
    2.16
    hoe
    2.11
    lot
    2.08
    eries
    2.04
    chaft
    1.88
     ago
    1.86
    Activations Density 0.085%

    No Known Activations