© 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. 22933
    Prev
    Next
    INDEX
    Explanations

    topics related to financial data and metrics

    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
    156
    +0.14
    0.8%
    66
    +0.11
    0.6%
    158
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.14
    0.58
    473
    +0.11
    0.56
    111
    +0.10
    0.55
    Negative Logits
    ?**
    -1.56
    documentclass
    -1.49
     windows
    -1.48
    nose
    -1.45
    rating
    -1.39
    fire
    -1.39
    izing
    -1.38
     window
    -1.37
    phosphory
    -1.36
    tered
    -1.36
    POSITIVE LOGITS
    Ļª
    3.48
    »¿
    3.20
    ĥ½
    3.14
    ĨĴ
    3.02
    Ĭ
    2.97
    į
    2.88
      ↵
    2.88
    <|outofrange|>
    2.87
    ↵
    2.87
    ↵↵
    2.87
    Activations Density 4.181%

    No Known Activations