© 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. 22932
    Prev
    Next
    INDEX
    Explanations

    terms related to specific religious groups and themes of loyalty or sacrifice

    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
    150
    +0.14
    0.8%
    63
    +0.13
    0.7%
    350
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.14
    0.06
    63
    +0.13
    0.07
    377
    +0.12
    0.06
    Negative Logits
     ours
    -1.77
    work
    -1.60
    washed
    -1.60
    conditioning
    -1.55
    inals
    -1.55
     shall
    -1.50
    forth
    -1.46
     redistribute
    -1.45
    soever
    -1.43
    ")]
    -1.43
    POSITIVE LOGITS
    µ
    4.68
    ª
    4.68
    ĵ
    4.52
    Ĵ
    4.40
    Ļ
    4.38
    Ģ
    4.34
    ī
    4.33
    ļ
    4.31
    ĨĴ
    4.31
    §
    4.26
    Activations Density 2.061%

    No Known Activations