© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27864
    Prev
    Next
    INDEX
    Explanations

    technical terms related to microservices and micro-level concepts

    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
    +0.23
    1.3%
    148
    +0.13
    0.8%
    391
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.23
    0.02
    391
    +0.13
    0.02
    2
    +0.12
    0.01
    Negative Logits
    arers
    -2.02
    ows
    -1.88
    emale
    -1.84
    unting
    -1.76
    unts
    -1.76
    ried
    -1.70
    arer
    -1.67
    ollowing
    -1.62
    arding
    -1.60
    ivat
    -1.52
    POSITIVE LOGITS
     sized
    1.59
    chip
    1.54
    stown
    1.51
     level
    1.49
    electronic
    1.48
     device
    1.45
    processor
    1.45
    phone
    1.41
     screens
    1.37
    castle
    1.34
    Activations Density 3.120%

    No Known Activations