© 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. 14524
    Prev
    Next
    INDEX
    Explanations

    references to laboratories and workspaces

    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
    25
    +0.13
    0.7%
    451
    +0.13
    0.7%
    208
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.13
    0.04
    145
    +0.13
    0.03
    368
    +0.12
    0.02
    Negative Logits
    Ĵ
    -2.59
    Ĥ
    -2.52
    ĸ
    -2.51
    Ĥ¬
    -2.50
    ²
    -2.46
    ½
    -2.37
    ª
    -2.35
    §
    -2.34
    ij
    -2.32
    Į
    -2.27
    POSITIVE LOGITS
    yrinth
    2.36
     automation
    2.22
     equipment
    2.13
     assistants
    2.02
     staff
    1.99
    ware
    1.98
    staff
    1.98
     technician
    1.96
    work
    1.95
    orers
    1.92
    Activations Density 0.504%

    No Known Activations