© 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 EvalsExportsinterp-engineNEWAPI 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. 13791
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "on."

    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
    59
    +0.14
    0.8%
    164
    +0.11
    0.6%
    463
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.02
    113
    +0.11
    0.03
    445
    +0.11
    0.01
    Negative Logits
    separated
    -1.54
    delim
    -1.48
    artan
    -1.46
    Ĺ
    -1.46
    "}](#
    -1.42
    {}{
    -1.41
     magnitude
    -1.38
     such
    -1.36
     forth
    -1.35
    DLL
    -1.33
    POSITIVE LOGITS
    look
    1.76
    cology
    1.75
     behalf
    1.75
    nel
    1.69
    atsu
    1.67
    acci
    1.64
    nes
    1.61
    eness
    1.60
    aught
    1.57
    iels
    1.56
    Activations Density 0.181%

    No Known Activations