© 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. 29921
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "with" in various contexts

    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
    478
    +0.15
    0.8%
    156
    +0.14
    0.8%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.15
    0.03
    102
    +0.14
    0.02
    356
    +0.12
    0.02
    Negative Logits
    xe
    -1.75
    "}](#
    -1.72
    piece
    -1.72
    headed
    -1.63
    phone
    -1.59
    head
    -1.50
    chair
    -1.48
    ")]
    -1.47
    /.
    -1.47
    lessness
    -1.45
    POSITIVE LOGITS
    ĻĤ
    2.59
     regard
    2.24
     respect
    2.08
     regards
    2.01
    Į
    2.00
    Ĭ
    1.96
    ľĵ
    1.92
    Ĥ¬
    1.87
     favor
    1.74
    ħ
    1.67
    Activations Density 0.130%

    No Known Activations