© 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. 28246
    Prev
    Next
    INDEX
    Explanations

    the phrase "commonly" used to describe general practices or trends

    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
    +0.14
    0.8%
    148
    +0.13
    0.7%
    87
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.14
    0.02
    352
    +0.13
    0.01
    257
    +0.13
    0.01
    Negative Logits
    fully
    -1.72
    ful
    -1.67
     integrity
    -1.65
    tle
    -1.58
    ector
    -1.50
    dk
    -1.48
     particular
    -1.47
    Engine
    -1.46
    board
    -1.42
    ñor
    -1.41
    POSITIVE LOGITS
     voiced
    1.50
     speaking
    1.45
     accessed
    1.42
     COUN
    1.36
    oche
    1.35
    )|^
    1.33
    ETHOD
    1.33
    UTH
    1.31
    owitz
    1.29
     warfare
    1.29
    Activations Density 0.363%

    No Known Activations