© 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. 9157
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    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
    21
    +0.16
    1.0%
    255
    +0.13
    0.8%
    248
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.16
    0.00
    21
    +0.13
    0.01
    78
    +0.12
    -0.00
    Negative Logits
    ching
    -1.63
     itself
    -1.60
    ably
    -1.42
     enjoyment
    -1.42
     thro
    -1.41
    omerase
    -1.38
    ifice
    -1.36
     training
    -1.32
     themselves
    -1.30
     skilled
    -1.29
    POSITIVE LOGITS
    ŀ
    2.94
    Ī
    2.89
    ¨
    2.86
    Ļª
    2.69
    Ĵ
    2.68
    ¢
    2.65
    ł
    2.58
    Ľ
    2.56
    £
    2.52
    ·¸
    2.52
    Activations Density 0.048%

    No Known Activations