© 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. 26312
    Prev
    Next
    INDEX
    Explanations

    adverbs related to the manner of performing 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/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
    130
    +0.12
    0.7%
    74
    +0.12
    0.7%
    47
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.12
    0.01
    242
    +0.12
    0.04
    130
    +0.10
    0.04
    Negative Logits
    Į
    -4.55
    -4.52
    <|outofrange|>
    -4.52
    <|outofrange|>
    -4.52
    ↵    ↵
    -4.52
    -4.52
    -4.52
    ↵
    -4.52
    ↵
    -4.52
    -4.52
    POSITIVE LOGITS
     allocated
    1.63
     adapted
    1.60
     eliminated
    1.58
     translated
    1.56
     killed
    1.56
     discharged
    1.54
     substituted
    1.54
     GENERATED
    1.54
     fired
    1.51
     Generated
    1.51
    Activations Density 0.174%

    No Known Activations