© 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. 13858
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" used frequently in phrases

    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
    466
    +0.19
    1.0%
    307
    +0.15
    0.8%
    478
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.19
    0.10
    402
    +0.15
    0.12
    330
    +0.15
    0.12
    Negative Logits
    Ħ
    -5.22
    ij
    -5.13
    µ
    -4.94
    ¸
    -4.90
    ¿½
    -4.80
    ¶
    -4.79
    ·
    -4.75
    ¾
    -4.75
    ĸ
    -4.71
    -4.68
    POSITIVE LOGITS
     then
    2.37
     forth
    2.11
     THEN
    2.05
     behold
    2.03
     hurry
    1.99
     replace
    1.90
     everything
    1.86
    then
    1.86
     hopefully
    1.85
     stuff
    1.82
    Activations Density 1.010%

    No Known Activations