© 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. 4-RES-SM
    11. 8838
    Prev
    Next
    INDEX
    Explanations

    coding constructs and structures related to programming, particularly in C++ or similar languages

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.15
    0.8%
    29
    +0.12
    0.7%
    35
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.15
    0.11
    78
    +0.12
    0.01
    148
    +0.11
    0.07
    Negative Logits
     ÂŃ
    -2.23
    .**]{}
    -1.57
    .''
    -1.48
    .]{}
    -1.48
    )]{}
    -1.44
    ]]>
    -1.41
    aan
    -1.32
     CAS
    -1.32
    .","
    -1.31
     ."
    -1.28
    POSITIVE LOGITS
    ::
    4.44
    ()->
    3.15
     ::
    2.98
    _->
    2.96
     std
    2.95
    ~
    2.94
    ı
    2.94
    >::
    2.74
    _;
    2.72
    ~,
    2.71
    Activations Density 1.816%

    No Known Activations