© 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. 15111
    Prev
    Next
    INDEX
    Explanations

    components of programming code, particularly related to event handling in a GUI

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    490
    +0.13
    0.7%
    181
    +0.12
    0.7%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.13
    0.03
    78
    +0.12
    -0.00
    255
    +0.12
    -0.01
    Negative Logits
    \];
    -1.55
    /](
    -1.53
     [[*
    -1.51
     justice
    -1.47
     ecosystem
    -1.44
    *]{}.
    -1.43
     onboard
    -1.43
     [<
    -1.42
    UTERS
    -1.42
     mayor
    -1.41
    POSITIVE LOGITS
    Dim
    2.12
    TextBox
    2.10
    1.93
    ↵
    1.93
    1.93
    ↵
    1.93
    ↵↵
    1.93
    1.93
    1.93
    č↵
    1.93
    Activations Density 0.332%

    No Known Activations