© 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. 2-RES-SM
    11. 26276
    Prev
    Next
    INDEX
    Explanations

    adverbs, particularly those describing manner or intensity

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.15
    0.8%
    450
    +0.12
    0.7%
    74
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.08
    288
    +0.12
    0.07
    156
    +0.12
    0.08
    Negative Logits
    ·¸
    -3.81
    ļ
    -3.69
    ħ
    -3.41
    Ĭ
    -3.41
    Į
    -3.37
    Ķ
    -3.25
    Īĺ
    -3.19
    Ĩ
    -3.18
    ¥
    -3.15
    ij
    -3.15
    POSITIVE LOGITS
     Wrote
    1.79
    vist
    1.71
    clic
    1.46
    rics
    1.43
    dict
    1.41
    comings
    1.40
    vre
    1.40
    adic
    1.39
    cles
    1.39
    aeda
    1.37
    Activations Density 0.532%

    No Known Activations