© 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. 29819
    Prev
    Next
    INDEX
    Explanations

    structured elements and attributes in programming or markup languages

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    271
    +0.14
    0.8%
    17
    +0.13
    0.7%
    136
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.14
    0.06
    410
    +0.13
    0.07
    498
    +0.12
    0.05
    Negative Logits
    ]:
    -1.73
    ppat
    -1.67
    .\[[@
    -1.61
    )</
    -1.58
    {$
    -1.56
    .[@
    -1.56
    *:
    -1.55
    ↵
    -1.53
    ktiv
    -1.51
     PubMed
    -1.51
    POSITIVE LOGITS
    Ļ
    3.05
    ´
    3.03
    ·¸
    3.02
    Ľ
    2.98
    ¡
    2.95
    ¼
    2.94
    ²
    2.94
    £
    2.90
    ī
    2.86
    ®
    2.85
    Activations Density 0.382%

    No Known Activations