© 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. 26926
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and dimensions

    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
    129
    +0.13
    0.7%
    503
    +0.12
    0.7%
    301
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.13
    0.03
    269
    +0.12
    0.02
    232
    +0.10
    0.02
    Negative Logits
     orders
    -1.64
     actors
    -1.58
    fires
    -1.54
     harm
    -1.50
     orphan
    -1.43
    matically
    -1.41
     products
    -1.39
    stitutional
    -1.38
     deadlines
    -1.37
     consequences
    -1.37
    POSITIVE LOGITS
    àµį
    1.69
    edo
    1.62
    à±į
    1.57
    ajan
    1.54
    à«ĩ
    1.51
    wise
    1.51
    eds
    1.50
    Sharp
    1.45
    à±ģ
    1.44
     Manager
    1.42
    Activations Density 0.071%

    No Known Activations