© 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. 4-RES-SM
    11. 15094
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in various contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    156
    +0.22
    1.3%
    291
    +0.15
    0.9%
    137
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.22
    0.09
    137
    +0.15
    0.09
    10
    +0.14
    0.08
    Negative Logits
    ī
    -3.26
    °
    -3.26
    º
    -3.23
    Ł
    -3.21
    Īĺ
    -3.17
    ł
    -3.14
    ģ
    -3.12
    Į
    -3.10
    ¤
    -3.10
    ¿
    -3.09
    POSITIVE LOGITS
     consequent
    2.99
     accompanying
    2.94
     ensuing
    2.55
     attendant
    2.48
     resultant
    2.46
     surrounding
    2.41
     rest
    2.40
     remainder
    2.29
     like
    2.21
     occasional
    2.16
    Activations Density 0.597%

    No Known Activations