© 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. 23552
    Prev
    Next
    INDEX
    Explanations

    legal terminology and court rulings

    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
    156
    +0.21
    1.2%
    97
    +0.11
    0.6%
    133
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.21
    0.02
    135
    +0.11
    0.02
    368
    +0.11
    0.01
    Negative Logits
    ---|---
    -1.56
    ---|---|---
    -1.54
     aisle
    -1.52
    ---|
    -1.51
    —.
    -1.47
     secrets
    -1.45
     Belt
    -1.44
     opportunity
    -1.34
     multiplicity
    -1.33
    )](#
    -1.32
    POSITIVE LOGITS
     responded
    1.70
    arios
    1.70
    ort
    1.69
    orts
    1.64
    ario
    1.60
    ortic
    1.45
    ous
    1.44
    aries
    1.42
    xit
    1.42
     reacted
    1.41
    Activations Density 0.871%

    No Known Activations