© 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 EvalsExportsAPI 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. 12660
    Prev
    Next
    INDEX
    Explanations

    import statements and class definitions related to user interface components

    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
    306
    +0.13
    0.7%
    21
    +0.13
    0.7%
    377
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.13
    -0.00
    126
    +0.13
    -0.00
    34
    +0.12
    0.03
    Negative Logits
     virgin
    -1.57
    ($_
    -1.56
    ?).
    -1.52
     ):
    -1.51
    coli
    -1.48
    apine
    -1.46
    phia
    -1.44
    dule
    -1.43
    cester
    -1.39
     suf
    -1.39
    POSITIVE LOGITS
    Ĥ¬
    2.45
    ©
    2.44
    º
    2.37
    ij
    2.34
    ½
    2.24
    Ļª
    2.23
    ŀ
    2.19
    ĩ
    2.15
    ¾
    2.13
    ĸ
    2.12
    Activations Density 0.156%

    No Known Activations