© 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. 9100
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or sequences

    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
    78
    +0.22
    1.3%
    21
    +0.13
    0.8%
    240
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.22
    0.00
    119
    +0.13
    0.01
    397
    +0.11
    0.01
    Negative Logits
     invention
    -1.64
     trier
    -1.45
    ines
    -1.45
    inine
    -1.43
    omerase
    -1.41
     itself
    -1.38
    idine
    -1.34
    inally
    -1.32
    ibrated
    -1.32
    aintiff
    -1.31
    POSITIVE LOGITS
    Ħ
    2.47
    İ
    2.36
    ĵ
    2.27
    IJ
    2.15
    ¡
    2.12
    ´
    2.12
    ª
    2.06
    Ĥ¬
    2.05
    ¸
    2.02
    Ĵ
    2.00
    Activations Density 0.081%

    No Known Activations