© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26690
    Prev
    Next
    INDEX
    Explanations

    financial terms and conditions related to insurance and payments

    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
    178
    +0.20
    1.1%
    271
    +0.15
    0.8%
    355
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.20
    0.13
    118
    +0.15
    0.15
    358
    +0.12
    0.11
    Negative Logits
    gage
    -1.73
     homem
    -1.66
     _________________________________
    -1.64
    ↵Č
    -1.54
     affiliate
    -1.52
     insurance
    -1.50
    ↵↵↵↵
    -1.48
     hereto
    -1.48
    ________________
    -1.47
    ↵↵↵↵↵
    -1.46
    POSITIVE LOGITS
    ĨĴ
    3.25
    ¾
    3.00
    Ī
    2.86
    ¿
    2.85
    Īĺ
    2.85
    ´
    2.83
    ·¸
    2.76
    »
    2.76
    ĭ
    2.74
    ł
    2.71
    Activations Density 3.800%

    No Known Activations