© 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. 1-RES-SM
    11. 29295
    Prev
    Next
    INDEX
    Explanations

    certain prepositions and terms related to digital content and replacement processes

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    126
    +0.13
    0.7%
    445
    +0.11
    0.6%
    289
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.04
    494
    +0.11
    0.02
    42
    +0.11
    0.01
    Negative Logits
     attention
    -1.42
     highlight
    -1.38
    ucer
    -1.33
    ite
    -1.33
     comprises
    -1.33
     winner
    -1.32
    middle
    -1.30
     stage
    -1.29
     representation
    -1.29
     couple
    -1.27
    POSITIVE LOGITS
    ¬
    1.75
    ·
    1.71
    µ
    1.68
    sein
    1.68
    ãģĨ
    1.58
    ŀ
    1.56
    iah
    1.55
    ¥
    1.53
    ©
    1.50
    BSD
    1.48
    Activations Density 0.131%

    No Known Activations