© 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. 25468
    Prev
    Next
    INDEX
    Explanations

    references to the Tamil ethnic group

    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
    71
    +0.15
    0.9%
    259
    +0.14
    0.8%
    182
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.01
    259
    +0.14
    0.01
    111
    +0.11
    0.01
    Negative Logits
    Ĺ
    -1.61
    ij
    -1.53
     TRI
    -1.51
     investigated
    -1.48
     assessed
    -1.46
    ķ
    -1.43
     sudden
    -1.41
    ĵ
    -1.41
     treated
    -1.41
      ↵
    -1.40
    POSITIVE LOGITS
    namese
    1.94
    ename
    1.88
    asek
    1.81
    amine
    1.76
    ieu
    1.75
    iny
    1.73
    endor
    1.70
    ERTY
    1.65
    obe
    1.63
    Åij
    1.62
    Activations Density 0.011%

    No Known Activations