© 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. 2-RES-SM
    11. 26499
    Prev
    Next
    INDEX
    Explanations

    definitions and declarations of data types in programming contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    47
    +0.26
    1.5%
    156
    +0.19
    1.1%
    240
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.26
    0.10
    240
    +0.19
    -0.01
    379
    +0.17
    0.09
    Negative Logits
    Figures
    -1.84
    \]](
    -1.81
    ĥ½
    -1.71
    odia
    -1.62
    ľĵ
    -1.60
    oons
    -1.58
    Figure
    -1.56
    noon
    -1.55
    ).](
    -1.54
    ¹
    -1.51
    POSITIVE LOGITS
     Haskell
    1.90
    ?",
    1.81
     lambda
    1.75
     ordinary
    1.72
     (__
    1.67
     #{
    1.66
     syscall
    1.65
     typeof
    1.64
     "!"
    1.64
     string
    1.62
    Activations Density 0.980%

    No Known Activations