© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25276
    Prev
    Next
    INDEX
    Explanations

    instances of the word "The."

    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
    23
    +0.40
    2.6%
    156
    +0.30
    2.0%
    478
    +0.23
    1.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.40
    0.11
    322
    +0.30
    0.09
    220
    +0.23
    0.09
    Negative Logits
    amente
    -1.75
    ENTIAL
    -1.75
    etto
    -1.73
    ophone
    -1.71
    ios
    -1.67
    ament
    -1.67
    oid
    -1.64
    room
    -1.63
    etable
    -1.59
    framework
    -1.59
    POSITIVE LOGITS
     following
    2.44
    rapy
    2.39
     same
    2.37
     easiest
    2.22
     latter
    2.15
     most
    2.12
    odor
    2.08
    oretical
    2.05
    rap
    2.05
     strongest
    2.05
    Activations Density 0.489%

    No Known Activations