© 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. 2-RES-SM
    11. 10273
    Prev
    Next
    INDEX
    Explanations

    references to software licenses and the Free Software Foundation

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    364
    +0.13
    0.8%
    251
    +0.13
    0.7%
    450
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.13
    0.03
    251
    +0.13
    0.02
    315
    +0.12
    0.02
    Negative Logits
    âĢ¦]
    -1.97
    []{
    -1.86
    ĻĤ
    -1.84
    .[]{
    -1.64
    Ł
    -1.63
    ĨĴ
    -1.63
    Ĺ
    -1.62
    ’.
    -1.54
    '):
    -1.54
    ’,
    -1.53
    POSITIVE LOGITS
     Bankruptcy
    1.52
     Library
    1.47
     Grove
    1.46
     Symphony
    1.41
     Editor
    1.40
     agent
    1.38
     infinite
    1.37
     insol
    1.36
    vens
    1.36
     editor
    1.35
    Activations Density 0.110%

    No Known Activations