© 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. 26871
    Prev
    Next
    INDEX
    Explanations

    references to bears and bear-related products

    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
    156
    +0.36
    2.2%
    354
    +0.12
    0.8%
    160
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.36
    0.10
    271
    +0.12
    -0.02
    160
    +0.11
    0.10
    Negative Logits
    ±
    -3.42
    ½
    -3.05
    -3.04
    ↵↵
    -3.04
    č↵
    -3.04
    ↵
    -3.04
    ↵  ↵
    -3.04
      ↵
    -3.04
    -3.04
    <|outofrange|>
    -3.04
    POSITIVE LOGITS
    apon
    1.68
     warrants
    1.66
    ancies
    1.59
     belongs
    1.58
    Processor
    1.54
     ${{
    1.51
    ships
    1.50
     contains
    1.48
    ship
    1.42
     deserves
    1.40
    Activations Density 1.978%

    No Known Activations