© 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 EvalsExportsAPI 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. 28539
    Prev
    Next
    INDEX
    Explanations

    references to the 21st century and the concept of frontiers

    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
    115
    +0.12
    0.7%
    156
    +0.12
    0.7%
    180
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.12
    0.01
    3
    +0.12
    0.01
    180
    +0.11
    0.01
    Negative Logits
     exceptions
    -1.77
     teachers
    -1.73
     others
    -1.69
    omers
    -1.57
     written
    -1.56
     respondents
    -1.52
     nurses
    -1.51
     aid
    -1.50
    ikh
    -1.50
     related
    -1.49
    POSITIVE LOGITS
    Ĭ
    3.43
    ½
    3.19
    ĩ
    3.19
      ↵
    3.19
    ↵
    3.19
    ↵
    3.19
    ↵
    3.19
    č↵č↵
    3.19
    ↵
    3.19
    ↵
    3.19
    Activations Density 0.009%

    No Known Activations