© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26421
    Prev
    Next
    INDEX
    Explanations

    legal references or citations in a court context

    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
    23
    +0.17
    1.0%
    258
    +0.15
    0.8%
    75
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.17
    0.04
    168
    +0.15
    0.03
    506
    +0.12
    0.03
    Negative Logits
    oretic
    -1.98
    buntu
    -1.65
    ocl
    -1.57
    per
    -1.55
    gran
    -1.52
    obi
    -1.46
    /@
    -1.45
    oker
    -1.45
    YPT
    -1.45
     :=
    -1.44
    POSITIVE LOGITS
    ¥
    2.98
    ĸ´
    2.96
    ĥ½
    2.94
    2.94
    ↵
    2.94
    ↵
    2.94
    ↵
    2.94
     ↵
    2.94
    ↵
    2.94
     ↵
    2.94
    Activations Density 0.136%

    No Known Activations