© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11374
    Prev
    Next
    INDEX
    Explanations

    guidelines and policies related to returns and shipping for purchased items

    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
    17
    +0.22
    1.2%
    263
    +0.14
    0.8%
    342
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.22
    -0.01
    57
    +0.14
    0.09
    387
    +0.14
    0.11
    Negative Logits
    ¾
    -3.54
    ±
    -3.48
    ļ
    -3.43
    ¯
    -3.43
    ij
    -3.42
    ł
    -3.33
    Ń
    -3.33
    ĨĴ
    -3.33
    ĸ
    -3.31
    ŀ
    -3.30
    POSITIVE LOGITS
     purchases
    2.29
     sale
    2.28
     retail
    2.20
     buyer
    2.17
     Retail
    2.17
     prices
    2.17
     retailers
    2.16
     buyers
    2.13
    gage
    2.11
     discounts
    2.07
    Activations Density 4.199%

    No Known Activations