© 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. 23928
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency or habitual actions

    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
    442
    +0.13
    0.7%
    171
    +0.13
    0.7%
    82
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.13
    0.07
    171
    +0.13
    0.07
    82
    +0.13
    0.07
    Negative Logits
    Ļª
    -2.83
    Ĵ
    -2.28
    ĨĴ
    -2.25
    Ħ
    -2.17
    ľ
    -2.13
    ļ
    -2.00
    Ģ
    -1.98
    ¦
    -1.96
    »¿
    -1.87
    ©
    -1.84
    POSITIVE LOGITS
    een
    1.68
     married
    1.67
     sne
    1.59
     forgot
    1.55
     recovered
    1.53
     worried
    1.51
     shed
    1.48
     offense
    1.46
     lose
    1.45
     wanna
    1.43
    Activations Density 0.741%

    No Known Activations