© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28268
    Prev
    Next
    INDEX
    Explanations

    instances of the word "interpretation" and its variations within legal contexts

    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
    156
    +0.17
    1.0%
    376
    +0.14
    0.8%
    392
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.17
    0.01
    493
    +0.14
    0.01
    392
    +0.11
    0.01
    Negative Logits
    »
    -1.82
    ]>
    -1.80
    jours
    -1.77
    ¿
    -1.53
    ½
    -1.53
    ĻĤ
    -1.53
    iday
    -1.50
    wards
    -1.49
    ATES
    -1.48
    pless
    -1.46
    POSITIVE LOGITS
    naire
    2.21
    ista
    1.65
     dictates
    1.64
    ulated
    1.52
    ensed
    1.51
    ally
    1.49
     aids
    1.46
    ually
    1.46
    arily
    1.45
     procedure
    1.45
    Activations Density 0.011%

    No Known Activations