© 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. 26398
    Prev
    Next
    INDEX
    Explanations

    instances of the word "large."

    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
    156
    +0.23
    1.3%
    376
    +0.15
    0.9%
    452
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.23
    0.01
    126
    +0.15
    0.01
    270
    +0.14
    0.01
    Negative Logits
     its
    -1.68
     theirs
    -1.68
    las
    -1.61
    urs
    -1.60
    arers
    -1.54
     ours
    -1.48
     mine
    -1.39
     Its
    -1.34
    iction
    -1.34
     patients
    -1.31
    POSITIVE LOGITS
    £
    2.57
    ĻĤ
    2.31
    Īĺ
    2.31
    ģ
    2.11
    ¿½
    2.04
     amounts
    2.03
    ª
    1.97
    ¾
    1.84
    »¿
    1.82
     quantities
    1.80
    Activations Density 0.317%

    No Known Activations