© 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. 12658
    Prev
    Next
    INDEX
    Explanations

    references to news publications and journalism-related terms

    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
    336
    +0.11
    0.6%
    24
    +0.11
    0.6%
    510
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.11
    0.06
    51
    +0.11
    0.11
    418
    +0.10
    0.02
    Negative Logits
    ĸ´
    -3.26
    Īĺ
    -3.21
    ĭ
    -3.03
    Į
    -3.00
    ĸ
    -2.94
    Ĺ
    -2.91
    Ł
    -2.90
    ĻĤ
    -2.88
    Ĭ
    -2.85
    IJ
    -2.83
    POSITIVE LOGITS
     editorial
    4.29
     journalism
    4.20
     newspapers
    3.73
     news
    3.58
     newspaper
    3.52
     editor
    3.52
     editors
    3.51
     publishing
    3.49
     journal
    3.47
     publication
    3.43
    Activations Density 2.104%

    No Known Activations