© 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. 26973
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements, possibly related to data or statistics

    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
    198
    +0.15
    0.9%
    369
    +0.14
    0.8%
    442
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.15
    0.02
    391
    +0.14
    0.07
    350
    +0.13
    0.12
    Negative Logits
    ]'
    -1.48
    ,’
    -1.46
     numbered
    -1.42
    ,'
    -1.37
    —'
    -1.37
     travelling
    -1.36
    erred
    -1.35
    tering
    -1.34
    wordpress
    -1.34
    ?’
    -1.33
    POSITIVE LOGITS
    sein
    1.73
    Ļª
    1.69
     sake
    1.56
    Ĭ
    1.55
      ↵
    1.53
                ↵
    1.53
    ↵
    1.53
    1.53
    1.53
    ↵
    1.53
    Activations Density 6.046%

    No Known Activations