© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 9362
    Prev
    Next
    INDEX
    Explanations

    structured data related to programming languages and web development technologies

    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
    156
    +0.27
    1.6%
    21
    +0.14
    0.8%
    177
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.27
    0.05
    312
    +0.14
    0.07
    98
    +0.14
    0.03
    Negative Logits
     deficit
    -1.64
    uation
    -1.57
     owed
    -1.51
     preponder
    -1.50
    isance
    -1.48
     compensation
    -1.45
    NEY
    -1.45
    abad
    -1.44
    ensation
    -1.42
    ulent
    -1.42
    POSITIVE LOGITS
     Android
    2.62
     Windows
    2.58
     Python
    2.56
     Linux
    2.49
     iOS
    2.49
     Chrome
    2.47
     Firefox
    2.46
     Ubuntu
    2.40
     Java
    2.39
     PHP
    2.39
    Activations Density 0.537%

    No Known Activations