© 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. 1-RES-SM
    11. 25846
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and their attributes

    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
    274
    +0.12
    0.7%
    458
    +0.12
    0.7%
    349
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.12
    0.03
    274
    +0.12
    0.03
    157
    +0.12
    0.03
    Negative Logits
    Ļª
    -2.67
    Ĭ
    -2.51
    ĨĴ
    -2.40
    IJ
    -2.22
    ¹
    -2.21
    ¿
    -2.14
    ¼
    -2.12
    ª
    -2.11
    ĻĤ
    -2.11
    Ĺ
    -2.10
    POSITIVE LOGITS
     criteria
    1.60
     punto
    1.59
     homepage
    1.59
     website
    1.53
    ibilit
    1.50
    rieved
    1.45
    ets
    1.41
    ftware
    1.39
     specialists
    1.38
     mirrors
    1.38
    Activations Density 0.369%

    No Known Activations