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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-SM
    11. 10962
    Prev
    Next
    INDEX
    Explanations

    references related to "per" and its various contexts or uses

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    322
    +0.14
    0.7%
    78
    +0.12
    0.6%
    174
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.14
    0.03
    241
    +0.12
    0.03
    322
    +0.11
    0.02
    Negative Logits
     respect
    -2.22
    hips
    -1.67
    ères
    -1.53
    egen
    -1.44
    oser
    -1.43
    ère
    -1.42
    ect
    -1.40
    érie
    -1.39
    unnumbered
    -1.39
    express
    -1.33
    POSITIVE LOGITS
    »¿
    3.59
    į
    3.52
    ¿
    3.32
    ĭ
    3.26
    »
    3.11
    ¾
    3.07
    ĵ
    3.02
    ij
    2.93
    Ĩ
    2.91
    ľ
    2.91
    Activations Density 0.086%

    No Known Activations