© 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. 11014
    Prev
    Next
    INDEX
    Explanations

    nested data structures or composite types in programming 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
    478
    +0.16
    0.9%
    47
    +0.14
    0.8%
    391
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.16
    0.03
    29
    +0.14
    0.02
    47
    +0.10
    0.04
    Negative Logits
    \]](
    -1.77
    oux
    -1.63
    ondo
    -1.62
     »
    -1.60
    )](
    -1.58
    ostic
    -1.53
    addy
    -1.50
    ued
    -1.49
    ustration
    -1.48
    rophy
    -1.48
    POSITIVE LOGITS
     Nations
    1.51
     extrac
    1.47
     nationals
    1.38
     outright
    1.38
     cardio
    1.36
     planets
    1.36
     civilian
    1.35
    hood
    1.34
    sem
    1.34
     diplomats
    1.33
    Activations Density 0.144%

    No Known Activations