© 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. 27515
    Prev
    Next
    INDEX
    Explanations

    instances of the word "handle"

    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
    282
    +0.15
    0.9%
    376
    +0.15
    0.9%
    468
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.15
    0.03
    148
    +0.15
    0.01
    282
    +0.14
    0.02
    Negative Logits
    illac
    -1.66
    sburg
    -1.58
    anni
    -1.53
    illion
    -1.51
    ienn
    -1.50
    ellar
    -1.48
    src
    -1.48
    sar
    -1.47
    esi
    -1.44
    unes
    -1.44
    POSITIVE LOGITS
    bars
    2.48
     affairs
    1.61
    ringes
    1.51
     handle
    1.45
    hov
    1.45
     handles
    1.44
     exercises
    1.41
    pez
    1.41
    hav
    1.38
     lately
    1.38
    Activations Density 0.197%

    No Known Activations