© 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 EvalsExportsAPI 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. 12665
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "om" and related variants

    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
    54
    +0.13
    0.7%
    21
    +0.11
    0.6%
    16
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.13
    0.02
    391
    +0.11
    0.03
    489
    +0.11
    0.02
    Negative Logits
    ger
    -1.63
     favour
    -1.50
    behind
    -1.40
    ctor
    -1.40
     favor
    -1.38
    MSO
    -1.38
    ivities
    -1.38
    ÑĢем
    -1.35
     CONTRIBUTORS
    -1.35
    \[
    -1.33
    POSITIVE LOGITS
    º
    3.63
    ·
    3.62
    ĺ
    3.48
    ¡
    3.45
    ¾
    3.40
    ľ
    3.35
    ¹
    3.34
    ij
    3.20
    ŀ
    3.19
    ±
    3.18
    Activations Density 0.094%

    No Known Activations