© 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. 2-RES-SM
    11. 31977
    Prev
    Next
    INDEX
    Explanations

    recurring references to daily activities and routines

    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
    29
    +0.12
    0.7%
    466
    +0.10
    0.6%
    501
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.12
    0.01
    404
    +0.10
    0.02
    41
    +0.10
    0.03
    Negative Logits
    Į
    -2.73
    IJ
    -2.67
    Ĵ
    -2.63
    ·¸
    -2.57
    ↵
    -2.56
    -2.56
    ↵
    -2.56
                ↵
    -2.56
    -2.56
       ↵
    -2.56
    POSITIVE LOGITS
    basis
    1.90
     Stats
    1.68
     observations
    1.66
     basis
    1.65
     magazine
    1.65
    ités
    1.61
     affairs
    1.60
    ción
    1.59
    ounce
    1.59
     newsletter
    1.57
    Activations Density 0.173%

    No Known Activations