© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 26424
    Prev
    Next
    INDEX
    Explanations

    technical terms related to statistical analyses and project development

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.18
    1.0%
    44
    +0.14
    0.8%
    419
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.18
    0.09
    266
    +0.14
    0.06
    200
    +0.13
    0.05
    Negative Logits
     mistaken
    -1.60
     ;;
    -1.48
    ply
    -1.36
    jest
    -1.35
    č↵					
    -1.34
    paper
    -1.33
     COURT
    -1.31
    ]{};
    -1.30
     PAGE
    -1.30
     mailing
    -1.29
    POSITIVE LOGITS
     respectively
    2.61
     alike
    2.48
     roles
    1.88
    ĻĤ
    1.71
     communities
    1.56
    Ŀ
    1.52
     analyses
    1.50
     importantly
    1.47
     industries
    1.46
     campaigns
    1.43
    Activations Density 2.017%

    No Known Activations