© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thanks

    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
    390
    +0.14
    0.8%
    73
    +0.12
    0.7%
    307
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.14
    0.02
    236
    +0.12
    0.03
    390
    +0.12
    0.03
    Negative Logits
    £
    -3.22
    Ń
    -3.12
    ī
    -3.10
    Īĺ
    -3.01
    ¿
    -2.99
    Ĩ
    -2.96
    -2.94
    ↵
    -2.94
    -2.94
    -2.94
    POSITIVE LOGITS
    giving
    2.22
     alot
    1.71
    bye
    1.59
    emplo
    1.56
     everyone
    1.53
     !
    1.52
     guys
    1.49
    edly
    1.48
     :)
    1.48
    away
    1.46
    Activations Density 0.066%

    No Known Activations