© 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. 29889
    Prev
    Next
    INDEX
    Explanations

    references to files or documentation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.15
    0.9%
    410
    +0.14
    0.8%
    129
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.15
    0.01
    410
    +0.14
    0.01
    129
    +0.11
    0.00
    Negative Logits
     distance
    -1.53
    ]{.
    -1.51
     life
    -1.49
    *](#
    -1.40
    ÅĦ
    -1.39
     radius
    -1.39
     homeostasis
    -1.38
     normal
    -1.33
     {}
    -1.33
     barrier
    -1.32
    POSITIVE LOGITS
    INGS
    2.24
    aced
    1.89
    ¨
    1.83
    ↵↵
    1.82
    ↵
    1.82
    ↵
    1.82
    ↵↵↵
    1.82
    1.82
    <|outofrange|>
    1.82
    1.82
    Activations Density 0.069%

    No Known Activations