© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28179
    Prev
    Next
    INDEX
    Explanations

    references to shared parameters or configurations in coding contexts

    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
    436
    +0.20
    1.2%
    369
    +0.20
    1.2%
    293
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.20
    0.12
    233
    +0.20
    0.09
    143
    +0.14
    0.07
    Negative Logits
    enberg
    -2.01
    wagen
    -1.85
    amas
    -1.64
     issue
    -1.61
    tera
    -1.60
    ench
    -1.57
    blogger
    -1.55
    /](
    -1.49
    visiae
    -1.48
    *](#
    -1.47
    POSITIVE LOGITS
     yourself
    1.85
     Methodist
    1.55
     {}
    1.44
     Missouri
    1.43
     whichever
    1.38
     yourselves
    1.35
     respectively
    1.34
     Mississippi
    1.33
    nez
    1.32
    counsel
    1.30
    Activations Density 5.991%

    No Known Activations