© 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. 4-RES-SM
    11. 9748
    Prev
    Next
    INDEX
    Explanations

    SQL-related commands and exceptions

    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
    357
    +0.21
    1.2%
    307
    +0.12
    0.6%
    49
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.21
    0.07
    405
    +0.12
    0.04
    57
    +0.10
    0.06
    Negative Logits
     skate
    -2.23
     Elsa
    -1.89
     Mickey
    -1.88
     sculpture
    -1.85
     painted
    -1.80
     skating
    -1.78
     helmet
    -1.78
     Animation
    -1.75
     Scul
    -1.73
     cartoon
    -1.71
    POSITIVE LOGITS
     SQL
    4.41
     MySQL
    4.20
    SQL
    4.13
    sql
    4.05
     mysql
    4.01
     sql
    3.96
    mysql
    3.87
     sqlite
    3.86
     Sql
    3.58
    Sql
    3.43
    Activations Density 0.747%

    No Known Activations