© 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. 4-RES-SM
    11. 12379
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to political contexts and issues

    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
    168
    +0.16
    0.9%
    137
    +0.15
    0.9%
    34
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.16
    0.04
    137
    +0.15
    0.04
    34
    +0.13
    0.04
    Negative Logits
    ĥ½
    -2.67
    ľĵ
    -2.56
    ľ
    -2.46
    »¿
    -2.36
    Ĭ
    -2.28
    ·¸
    -2.19
    ĥ
    -2.17
    ¶
    -2.17
    ½
    -2.10
    ĸ´
    -1.99
    POSITIVE LOGITS
     affiliation
    2.13
     correctness
    2.06
     affairs
    1.98
     affiliations
    1.97
     activism
    1.97
     leaders
    1.96
     views
    1.87
     persu
    1.86
     campaigning
    1.84
     campaigns
    1.81
    Activations Density 0.188%

    No Known Activations