© 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. 1-RES-SM
    11. 28829
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence-ending structures

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    352
    +0.12
    0.7%
    500
    +0.12
    0.7%
    410
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.12
    0.03
    136
    +0.12
    -0.01
    352
    +0.10
    0.04
    Negative Logits
    º
    -1.94
    ĸ
    -1.89
    documentclass
    -1.89
    ¬
    -1.84
    ¢
    -1.80
    Ķ
    -1.77
    ·¸
    -1.74
    »
    -1.74
    ¦
    -1.71
    Ĵ
    -1.71
    POSITIVE LOGITS
    enstein
    1.58
    pole
    1.54
     or
    1.51
    arthy
    1.50
    nikov
    1.46
    imir
    1.42
     motion
    1.37
     argument
    1.36
     shoes
    1.36
    iani
    1.34
    Activations Density 0.550%

    No Known Activations