© 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. 13567
    Prev
    Next
    INDEX
    Explanations

    CSS properties and layout styles in web design

    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
    129
    +0.14
    0.8%
    21
    +0.14
    0.8%
    220
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.14
    0.04
    185
    +0.14
    0.03
    220
    +0.13
    0.04
    Negative Logits
     toll
    -1.58
    arner
    -1.50
    ystems
    -1.49
    )."
    -1.46
     ))
    -1.46
    .")
    -1.46
    ycin
    -1.45
    _**
    -1.44
    )].
    -1.43
    gio
    -1.40
    POSITIVE LOGITS
    ı
    2.90
    Ļª
    2.69
    ¡
    2.56
    ³
    2.50
    IJ
    2.40
    į
    2.39
    Į
    2.36
    µ
    2.31
    ij
    2.29
    ĸ
    2.26
    Activations Density 0.256%

    No Known Activations