© 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. 28273
    Prev
    Next
    INDEX
    Explanations

    references to ownership or possession of something

    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
    156
    +0.22
    1.2%
    338
    +0.14
    0.8%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.22
    0.03
    410
    +0.14
    0.04
    171
    +0.13
    0.02
    Negative Logits
     ours
    -1.67
    imit
    -1.63
     minors
    -1.57
    riminal
    -1.55
    imetric
    -1.47
    inite
    -1.47
     MERCHANTABILITY
    -1.43
    ifications
    -1.42
    YPT
    -1.41
    mining
    -1.41
    POSITIVE LOGITS
    ª
    3.87
    ±
    3.50
    ³
    3.48
    µ
    3.41
    ©
    3.39
    IJ
    3.39
    Ĥ
    3.37
    ¶
    3.34
    ¤
    3.28
    į
    3.28
    Activations Density 0.109%

    No Known Activations