© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 11201
    Prev
    Next
    INDEX
    Explanations

    references to specific legal or regulatory codes

    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
    369
    +0.30
    1.8%
    156
    +0.16
    0.9%
    377
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.30
    0.05
    377
    +0.16
    0.06
    469
    +0.14
    0.04
    Negative Logits
    vez
    -1.73
    xico
    -1.64
    eries
    -1.53
     new
    -1.51
    beit
    -1.51
    idious
    -1.51
    ptions
    -1.50
     forth
    -1.50
    ureus
    -1.49
    ption
    -1.47
    POSITIVE LOGITS
    OUBLE
    2.34
    olphin
    1.95
    REAM
    1.94
    warf
    1.90
    irection
    1.88
    irected
    1.66
    rops
    1.66
    yne
    1.65
    oubt
    1.65
    ifference
    1.65
    Activations Density 0.128%

    No Known Activations