© 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. 1-RES-SM
    11. 24381
    Prev
    Next
    INDEX
    Explanations

    references to payment or financial transactions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    55
    +0.11
    0.6%
    166
    +0.10
    0.6%
    320
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.11
    0.04
    462
    +0.10
    0.03
    320
    +0.10
    0.03
    Negative Logits
    £
    -3.01
    ¿½
    -2.66
    Īĺ
    -2.64
    Ń
    -2.63
    ¨
    -2.56
    ³
    -2.56
    »
    -2.51
    Ŀ
    -2.49
    ¬
    -2.48
    ª
    -2.48
    POSITIVE LOGITS
    mium
    1.90
    back
    1.77
    check
    1.60
    own
    1.60
    pal
    1.55
    lot
    1.51
    elike
    1.50
    onde
    1.46
    offs
    1.45
    rier
    1.40
    Activations Density 0.180%

    No Known Activations