© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 12010
    Prev
    Next
    INDEX
    Explanations

    terms related to government and political systems

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.26
    1.6%
    29
    +0.12
    0.7%
    137
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.26
    0.07
    137
    +0.12
    0.08
    11
    +0.11
    0.05
    Negative Logits
    ĨĴ
    -2.07
    ĥ½
    -2.07
    į
    -1.76
    osterone
    -1.69
    avirus
    -1.69
    Ļª
    -1.67
    Ģ
    -1.64
    ¹
    -1.55
    itives
    -1.53
    Ī
    -1.51
    POSITIVE LOGITS
     districts
    2.04
     district
    2.00
     centre
    1.95
     department
    1.92
     organisation
    1.91
     subdivision
    1.90
     north
    1.85
     affairs
    1.84
     zone
    1.83
     council
    1.82
    Activations Density 0.533%

    No Known Activations