© 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. 9649
    Prev
    Next
    INDEX
    Explanations

    references to directories and listings related to specific organizations or institutions

    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
    156
    +0.19
    1.1%
    307
    +0.15
    0.9%
    418
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.19
    0.15
    156
    +0.15
    0.15
    510
    +0.15
    0.15
    Negative Logits
    ŀ
    -1.95
    į
    -1.75
    ¹
    -1.74
     paraly
    -1.59
    µ
    -1.58
    ľ
    -1.54
    ¾
    -1.54
    Ŀ
    -1.54
    ¤
    -1.53
     injected
    -1.53
    POSITIVE LOGITS
     lists
    2.81
     listed
    2.69
     listings
    2.62
    listed
    2.52
     listing
    2.47
     list
    2.43
     numbered
    2.34
     names
    2.33
    ↵↵
    2.31
     rankings
    2.26
    Activations Density 2.386%

    No Known Activations