© 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. 2-MLP-SM
    11. 23406
    Prev
    Next
    INDEX
    Explanations

    the word "that" 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/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
    499
    +0.12
    0.7%
    423
    +0.12
    0.7%
    459
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.12
    0.07
    502
    +0.12
    0.07
    284
    +0.11
    0.05
    Negative Logits
     residue
    -1.53
    ously
    -1.49
     unity
    -1.49
    cke
    -1.47
     mercury
    -1.46
     hypothesis
    -1.46
     \$
    -1.39
     dark
    -1.38
    us
    -1.38
     chromium
    -1.35
    POSITIVE LOGITS
    áĢ¯
    2.05
    à³
    2.02
    áĢ¸
    1.98
    áĢº
    1.93
    áŁ
    1.86
    áĢ¬
    1.84
    áĢIJ
    1.81
    ி
    1.78
    à²
    1.69
    à¯
    1.65
    Activations Density 0.412%

    No Known Activations