© 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. 14395
    Prev
    Next
    INDEX
    Explanations

    plans, schedules, or events related to activities and arrangements

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    293
    +0.14
    0.8%
    331
    +0.13
    0.8%
    419
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.14
    0.12
    56
    +0.13
    -0.04
    331
    +0.13
    0.09
    Negative Logits
    ı
    -2.51
    ĻĤ
    -2.50
    ·¸
    -2.45
    ľĵ
    -2.42
    «
    -2.38
    »¿
    -2.38
    ±
    -2.34
    į
    -2.28
    ī
    -2.28
    Ī
    -2.26
    POSITIVE LOGITS
     evacuation
    1.60
     tours
    1.55
    erty
    1.53
     remed
    1.52
    cular
    1.47
    isciplinary
    1.44
     renov
    1.42
     retirement
    1.41
    �
    1.40
     restructuring
    1.39
    Activations Density 4.043%

    No Known Activations