© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27420
    Prev
    Next
    INDEX
    Explanations

    terms related to rental engines and customer service in logistics

    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
    130
    +0.11
    0.7%
    477
    +0.11
    0.7%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.11
    0.02
    487
    +0.11
    0.02
    321
    +0.11
    0.02
    Negative Logits
     latter
    -1.80
    lay
    -1.60
     sight
    -1.58
     ");
    -1.57
     endl
    -1.56
     Anyway
    -1.55
    inner
    -1.54
     '</
    -1.53
    tbody
    -1.53
    rier
    -1.50
    POSITIVE LOGITS
    ¼
    2.83
    ĸ
    2.53
    Ĩ
    2.49
    ī
    2.47
    ĸ´
    2.37
    º
    2.36
    ½
    2.33
    Ľ
    2.29
    Ģ
    2.24
    Ŀ
    2.19
    Activations Density 0.144%

    No Known Activations