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

    Neuronpedia

    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. 26632
    Prev
    Next
    INDEX
    Explanations

    terms related to the recurrence and relapse of medical conditions

    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
    30
    +0.13
    0.7%
    156
    +0.13
    0.7%
    184
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.02
    271
    +0.13
    0.00
    156
    +0.10
    0.02
    Negative Logits
    ½
    -2.73
    »¿
    -2.57
    º
    -2.54
    ĻĤ
    -2.53
    ĥ½
    -2.49
    -2.48
    -2.48
      ↵
    -2.48
    ↵
    -2.48
    -2.48
    POSITIVE LOGITS
     occurring
    2.13
    arial
    1.86
    atics
    1.71
    nikov
    1.63
     rate
    1.59
     posterior
    1.57
    als
    1.56
     phase
    1.55
     rates
    1.54
    ional
    1.54
    Activations Density 0.068%

    No Known Activations