© 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. 14110
    Prev
    Next
    INDEX
    Explanations

    occurrences of slashes or division symbols

    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
    204
    +0.14
    0.8%
    25
    +0.12
    0.7%
    297
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.14
    0.04
    50
    +0.12
    0.03
    203
    +0.12
    0.04
    Negative Logits
    esium
    -1.66
    omy
    -1.52
     herein
    -1.49
    eful
    -1.47
     regards
    -1.47
    ylase
    -1.47
    ocardi
    -1.46
     function
    -1.45
    asma
    -1.43
    ocene
    -1.40
    POSITIVE LOGITS
    ¿
    4.66
    ¾
    4.62
    §
    4.62
    ¦
    4.60
    ½
    4.58
    ¤
    4.56
    Ĺ
    4.45
    ¯
    4.45
    IJ
    4.41
    Ļª
    4.38
    Activations Density 0.128%

    No Known Activations