© 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. 28183
    Prev
    Next
    INDEX
    Explanations

    dates, specifically the occurrence of "Dec 10."

    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
    444
    +0.15
    0.8%
    369
    +0.14
    0.7%
    328
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.15
    0.03
    328
    +0.14
    0.03
    281
    +0.14
    0.03
    Negative Logits
    rias
    -2.01
     minor
    -1.73
     midst
    -1.58
     corrections
    -1.56
     utmost
    -1.53
     true
    -1.50
    mit
    -1.46
     Dominican
    -1.43
     burden
    -1.42
     him
    -1.42
    POSITIVE LOGITS
    iseconds
    1.67
    uet
    1.67
    idable
    1.62
    isecond
    1.60
    oded
    1.58
    ellular
    1.57
    kered
    1.57
    ipher
    1.54
    seek
    1.54
    adin
    1.53
    Activations Density 0.208%

    No Known Activations