© 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. 29452
    Prev
    Next
    INDEX
    Explanations

    phrases indicating foundational principles or criteria

    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
    376
    +0.16
    0.9%
    83
    +0.12
    0.7%
    504
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.16
    0.03
    504
    +0.12
    0.03
    339
    +0.10
    0.02
    Negative Logits
    aney
    -1.66
    ellow
    -1.50
     Esq
    -1.48
    ingle
    -1.46
     shame
    -1.42
    .)
    -1.41
    akin
    -1.41
     succeed
    -1.40
    >`
    -1.36
     partisan
    -1.36
    POSITIVE LOGITS
    notes
    1.79
    stock
    1.71
    amente
    1.67
    emann
    1.60
    plant
    1.60
    bles
    1.58
    ière
    1.58
    nuts
    1.54
    als
    1.52
    ats
    1.49
    Activations Density 0.024%

    No Known Activations