© 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. 9014
    Prev
    Next
    INDEX
    Explanations

    references to the name "Dar" in various contexts

    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
    369
    +0.18
    1.0%
    410
    +0.15
    0.9%
    439
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.18
    0.02
    410
    +0.15
    0.03
    448
    +0.12
    0.03
    Negative Logits
    ed
    -2.27
    er
    -1.95
    hift
    -1.87
    eria
    -1.73
     paper
    -1.65
    edes
    -1.61
     spectrum
    -1.59
     membrane
    -1.54
    orems
    -1.53
    ede
    -1.53
    POSITIVE LOGITS
    ryl
    2.92
    lington
    2.60
    rell
    2.12
    ÃŃo
    2.11
    ½
    2.11
    ren
    2.03
    rington
    1.94
    win
    1.90
    cy
    1.87
    ling
    1.82
    Activations Density 0.180%

    No Known Activations