© 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. MLP Post
    9. 2-MLP-SM
    11. 24578
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the future

    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/2-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.2.hook_mlp_out
    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
    358
    +0.14
    0.8%
    369
    +0.12
    0.6%
    94
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    94
    +0.14
    0.03
    335
    +0.12
    0.03
    358
    +0.11
    0.03
    Negative Logits
     outlook
    -1.62
     view
    -1.56
    ory
    -1.54
    inib
    -1.47
    ARY
    -1.46
    erd
    -1.39
     Boltzmann
    -1.37
     views
    -1.36
    igan
    -1.35
    ucht
    -1.30
    POSITIVE LOGITS
    quartile
    1.69
    *\*
    1.68
    defendants
    1.55
    $)
    1.55
    #{$
    1.53
    tails
    1.51
    amination
    1.48
    lique
    1.46
    blockList
    1.45
    ĸ
    1.42
    Activations Density 0.348%

    No Known Activations