© 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. 2-RES-SM
    11. 27412
    Prev
    Next
    INDEX
    Explanations

    Java package imports, specifically those related to the org namespace

    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
    365
    +0.12
    0.7%
    87
    +0.11
    0.6%
    417
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.12
    0.03
    352
    +0.11
    0.03
    494
    +0.11
    0.03
    Negative Logits
     contrary
    -1.50
      ↵
    -1.49
     consequence
    -1.49
     aren
    -1.44
     deadline
    -1.41
     [âĢ¦]
    -1.41
     chances
    -1.41
    ores
    -1.40
    ories
    -1.40
     *)
    -1.38
    POSITIVE LOGITS
    ģ
    1.78
    Ģ
    1.61
    udo
    1.60
    asm
    1.58
    red
    1.55
    member
    1.54
    ³
    1.53
    Īĺ
    1.50
    usted
    1.48
    iom
    1.46
    Activations Density 0.078%

    No Known Activations