© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22359
    Prev
    Next
    INDEX
    Explanations

    legal terminology and contractual obligations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.14
    0.8%
    478
    +0.13
    0.7%
    61
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.14
    0.05
    275
    +0.13
    -0.00
    61
    +0.12
    0.05
    Negative Logits
    à±ģ
    -2.15
    à±į
    -1.79
    ector
    -1.71
    à¯ģ
    -1.63
    à°¿
    -1.62
    iances
    -1.61
    áĢ¬
    -1.60
    als
    -1.58
    oster
    -1.56
    à¯į
    -1.55
    POSITIVE LOGITS
    §
    1.88
    ¿½
    1.87
    plist
    1.81
    º
    1.70
    ,**
    1.65
    Ĺ
    1.61
     gravel
    1.56
    ¿
    1.53
    ©
    1.51
    bbe
    1.49
    Activations Density 0.586%

    No Known Activations