© 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. 1-RES-SM
    11. 24517
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events

    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
    23
    +0.24
    1.5%
    438
    +0.13
    0.9%
    478
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.24
    0.17
    338
    +0.13
    0.15
    53
    +0.11
    0.13
    Negative Logits
    malloc
    -1.62
    oha
    -1.59
    enstein
    -1.56
    ajas
    -1.56
    bal
    -1.54
    itious
    -1.50
    fu
    -1.50
    icles
    -1.50
    bourne
    -1.49
    yards
    -1.48
    POSITIVE LOGITS
    ĥ½
    3.65
    ķ
    3.51
    Ī
    3.49
    ŀ
    3.36
    ¿½
    3.32
    ĵ
    3.29
      ↵
    3.28
     ↵
    3.28
    3.28
    3.28
    Activations Density 0.971%

    No Known Activations