© 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. MLP Post
    9. 0-MLP-SM
    11. 29668
    Prev
    Next
    INDEX
    Explanations

    references to the variable 'R' in computing or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    412
    +0.17
    1.0%
    369
    +0.17
    1.0%
    362
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.17
    0.06
    191
    +0.17
    0.05
    429
    +0.14
    0.05
    Negative Logits
    resis
    -2.20
    eing
    -1.77
    xture
    -1.71
     hurry
    -1.64
     realise
    -1.60
    ability
    -1.60
    cause
    -1.58
    irc
    -1.53
    acity
    -1.51
    cket
    -1.48
    POSITIVE LOGITS
    aspberry
    1.68
    endered
    1.66
    âĢIJ
    1.61
    PG
    1.59
    PL
    1.55
    google
    1.52
    anks
    1.52
    BIO
    1.51
    STA
    1.50
    abi
    1.47
    Activations Density 0.032%

    No Known Activations