© 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. 23300
    Prev
    Next
    INDEX
    Explanations

    concepts related to morality and divine revelation

    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
    23
    +0.25
    1.4%
    111
    +0.12
    0.7%
    155
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.25
    0.14
    139
    +0.12
    0.12
    120
    +0.12
    0.13
    Negative Logits
     etc
    -2.04
    etc
    -1.71
    ographies
    -1.71
    istical
    -1.66
     teaches
    -1.63
    ira
    -1.63
    emis
    -1.61
    craft
    -1.59
    arch
    -1.59
    making
    -1.57
    POSITIVE LOGITS
    ]>
    1.68
    '>
    1.54
     penet
    1.47
    '\
    1.44
    liest
    1.43
     curly
    1.42
     '#
    1.39
    reland
    1.38
    >]
    1.38
    lick
    1.37
    Activations Density 1.994%

    No Known Activations