© 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 EvalsExportsAPI 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. 11055
    Prev
    Next
    INDEX
    Explanations

    the letter "M" in various contexts

    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
    369
    +0.15
    0.8%
    271
    +0.13
    0.8%
    391
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.15
    0.04
    391
    +0.13
    0.06
    11
    +0.12
    0.04
    Negative Logits
    ctions
    -2.02
    ference
    -1.73
    ction
    -1.73
    iper
    -1.69
     itself
    -1.68
    ibility
    -1.68
    valence
    -1.62
    ters
    -1.60
    icial
    -1.56
    eless
    -1.55
    POSITIVE LOGITS
    Į
    3.56
    ı
    3.46
    ª
    3.41
    ĨĴ
    3.28
    IJ
    3.17
    ī
    3.16
    Ļª
    3.11
    ¦
    3.09
    ĺ
    3.09
    Ĺ
    3.08
    Activations Density 0.074%

    No Known Activations