© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23900
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking advantage of opportunities or offers

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    198
    +0.16
    0.9%
    73
    +0.12
    0.7%
    15
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.04
    378
    +0.12
    0.07
    46
    +0.11
    0.04
    Negative Logits
    ĻĤ
    -4.25
    -3.90
    ↵
    -3.90
    -3.90
    ↵
    -3.90
            ↵
    -3.90
    č↵
    -3.90
    -3.90
    -3.90
    -3.90
    POSITIVE LOGITS
     resistance
    1.52
     0000000000000000000000000000000000
    1.51
     inert
    1.49
     oxygen
    1.46
     trac
    1.42
     taut
    1.41
    ferentially
    1.41
     raft
    1.37
    cknow
    1.36
    erent
    1.33
    Activations Density 0.642%

    No Known Activations