© 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 EvalsExportsinterp-engineNEWAPI 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. 9342
    Prev
    Next
    INDEX
    Explanations

    components related to user interface and layout structures in code

    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
    78
    +0.14
    0.8%
    74
    +0.14
    0.8%
    379
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.14
    0.02
    452
    +0.14
    0.01
    379
    +0.11
    0.02
    Negative Logits
    thon
    -1.51
     living
    -1.39
     petitioner
    -1.38
     therein
    -1.35
     future
    -1.34
     Canad
    -1.33
     -,
    -1.31
     [@
    -1.31
     exem
    -1.25
     hereafter
    -1.22
    POSITIVE LOGITS
    ı
    4.75
    ³
    4.66
    ĨĴ
    4.57
    £
    4.40
    Ĵ
    4.38
    Ļª
    4.38
    Ŀ
    4.19
    ¢
    4.17
    ª
    4.15
    ĵ
    4.15
    Activations Density 0.085%

    No Known Activations