© 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. 2-RES-SM
    11. 30169
    Prev
    Next
    INDEX
    Explanations

    terms related to wireless technology

    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
    156
    +0.28
    1.6%
    292
    +0.11
    0.7%
    443
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.28
    0.02
    429
    +0.11
    0.02
    173
    +0.10
    0.01
    Negative Logits
     tears
    -1.81
     repent
    -1.73
     unexpected
    -1.71
    heets
    -1.66
     certain
    -1.57
     miscar
    -1.56
     deciding
    -1.53
     happier
    -1.52
     unhappy
    -1.51
     daunting
    -1.51
    POSITIVE LOGITS
    ¡
    3.02
    Ī
    2.91
    Ħ
    2.90
    ŀ
    2.88
    ķ
    2.88
    ħ
    2.85
    ¢
    2.79
    ĸ
    2.77
    Ĵ
    2.75
    Ģ
    2.67
    Activations Density 0.121%

    No Known Activations