© 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. 1-RES-SM
    11. 29771
    Prev
    Next
    INDEX
    Explanations

    programming keywords and terms related to data structures and management in software

    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
    157
    +0.16
    0.9%
    210
    +0.14
    0.8%
    59
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.16
    0.08
    369
    +0.14
    0.04
    348
    +0.13
    0.07
    Negative Logits
    »¿
    -1.43
     growing
    -1.42
    use
    -1.42
    deal
    -1.39
     colour
    -1.38
    *](#
    -1.37
    said
    -1.36
     estimated
    -1.36
    vast
    -1.36
    549
    -1.33
    POSITIVE LOGITS
    atable
    1.87
     yourself
    1.70
     rpm
    1.67
     %{
    1.60
     yourselves
    1.55
    }",
    1.52
     },
    1.51
     yours
    1.50
    ersion
    1.50
     GitHub
    1.46
    Activations Density 0.796%

    No Known Activations