© 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. 30590
    Prev
    Next
    INDEX
    Explanations

    the preposition "on" used in various contexts

    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
    478
    +0.20
    1.1%
    47
    +0.14
    0.8%
    69
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.20
    0.06
    243
    +0.14
    0.05
    282
    +0.14
    0.04
    Negative Logits
    ifice
    -1.55
     induct
    -1.54
     inhibitors
    -1.47
    ^](#
    -1.46
     glyc
    -1.46
     BGCOLOR
    -1.46
     Pradesh
    -1.45
     proceeds
    -1.45
    ifically
    -1.41
     Scholars
    -1.41
    POSITIVE LOGITS
     behalf
    2.79
    boarding
    2.12
    cology
    2.05
    shore
    2.01
    loaded
    1.88
    eday
    1.81
    yx
    1.81
    ismiss
    1.72
    ovo
    1.69
    ze
    1.69
    Activations Density 0.199%

    No Known Activations