© 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. 29159
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it"

    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
    439
    +0.14
    0.8%
    225
    +0.12
    0.7%
    375
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.14
    0.22
    185
    +0.12
    0.17
    165
    +0.12
    0.17
    Negative Logits
    ¹
    -2.45
    Ļ
    -2.36
    ĨĴ
    -2.19
    ĭ
    -2.02
    į
    -1.98
    Ī
    -1.94
    ´
    -1.92
    ŀ
    -1.91
    Ĭ
    -1.91
    Ł
    -1.90
    POSITIVE LOGITS
    .[]{
    1.68
    ↵Č
    1.62
    *](#
    1.53
    LES
    1.50
     (`
    1.47
    oles
    1.44
    .]
    1.42
    .]{}
    1.41
    ↵↵↵↵↵
    1.40
    stairs
    1.40
    Activations Density 0.410%

    No Known Activations