© 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. 10211
    Prev
    Next
    INDEX
    Explanations

    specific names and references related to notable events and awards in the entertainment industry

    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
    307
    +0.26
    1.5%
    156
    +0.24
    1.4%
    271
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.26
    0.04
    271
    +0.24
    0.01
    469
    +0.17
    0.06
    Negative Logits
     BASIS
    -1.53
     _________________________________
    -1.51
     ##
    -1.38
     https
    -1.35
     etc
    -1.31
     accordingly
    -1.30
     infra
    -1.30
     OF
    -1.30
     JP
    -1.29
     ?
    -1.29
    POSITIVE LOGITS
    ·¸
    6.05
    ĻĤ
    5.71
    «
    5.56
    ¼
    5.44
    ı
    5.42
    º
    5.38
    ´
    5.30
    Ļª
    5.29
    ĨĴ
    5.28
    Ļ
    5.27
    Activations Density 0.565%

    No Known Activations