© 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. 26154
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various 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
    390
    +0.11
    0.6%
    144
    +0.11
    0.6%
    475
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.11
    0.47
    98
    +0.11
    0.21
    228
    +0.11
    0.32
    Negative Logits
    ®
    -1.89
     chromosome
    -1.56
     Syndrome
    -1.51
    ENTS
    -1.50
    ylene
    -1.49
    ¶
    -1.44
    .
    -1.43
    $(
    -1.43
    atta
    -1.37
    équ
    -1.35
    POSITIVE LOGITS
    xt
    1.63
    urally
    1.60
     wand
    1.56
     gun
    1.55
    gun
    1.51
     weapon
    1.48
    XM
    1.45
    uous
    1.44
    eenth
    1.42
    ety
    1.40
    Activations Density 2.899%

    No Known Activations