© 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. 24143
    Prev
    Next
    INDEX
    Explanations

    references to divine qualities and concepts of love and service

    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
    384
    +0.10
    0.6%
    433
    +0.10
    0.5%
    456
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.10
    0.13
    155
    +0.10
    0.18
    191
    +0.10
    0.15
    Negative Logits
    ĭ
    -2.75
    Ĺ
    -2.55
    Ĭ
    -2.52
    ĥ½
    -2.30
    ĩ
    -2.30
    ĸ
    -2.30
    ĵ
    -2.26
    į
    -2.24
    Ĵ
    -2.23
    Ł
    -2.23
    POSITIVE LOGITS
    hereinafter
    1.68
    RSP
    1.63
     Inspector
    1.50
    idently
    1.50
    ême
    1.47
    issa
    1.43
    described
    1.43
    Enron
    1.42
    denly
    1.42
    terday
    1.41
    Activations Density 5.075%

    No Known Activations