© 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. 25914
    Prev
    Next
    INDEX
    Explanations

    references to political concepts and terminology

    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
    156
    +0.22
    1.3%
    219
    +0.11
    0.7%
    501
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.22
    0.03
    501
    +0.11
    0.03
    78
    +0.11
    0.03
    Negative Logits
    ľ
    -2.08
    ĥ½
    -2.01
    Ĭ
    -1.96
    Ŀ
    -1.91
    ľĵ
    -1.89
    ½
    -1.73
    IJ
    -1.72
    Ķ
    -1.72
    ¶
    -1.66
    ĸ´
    -1.56
    POSITIVE LOGITS
    thirds
    2.08
    ised
    1.69
     behind
    1.61
    acters
    1.59
    ically
    1.57
     correctness
    1.57
    izer
    1.57
    iary
    1.56
    isms
    1.56
    Inflater
    1.55
    Activations Density 0.128%

    No Known Activations