© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15055
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names related to locations and organizations

    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
    +0.39
    2.5%
    78
    +0.13
    0.9%
    158
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.39
    0.11
    255
    +0.13
    0.01
    450
    +0.11
    0.04
    Negative Logits
    ishly
    -1.50
    rent
    -1.30
     halls
    -1.28
     stakes
    -1.26
     reck
    -1.25
     licenses
    -1.20
    ctions
    -1.16
     respect
    -1.16
    ingly
    -1.16
     realization
    -1.15
    POSITIVE LOGITS
    ħ
    3.20
    ı
    3.14
    ī
    3.11
    Į
    3.07
    Ķ
    3.04
    ¹
    3.02
    Ħ
    2.97
    Ļ
    2.91
    ĭ
    2.89
    į
    2.85
    Activations Density 0.841%

    No Known Activations