© 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 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. 29087
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "None" or "absence."

    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
    436
    +0.14
    0.8%
    247
    +0.12
    0.7%
    483
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.14
    0.02
    353
    +0.12
    0.02
    483
    +0.10
    0.02
    Negative Logits
    its
    -1.69
     millions
    -1.65
     thousands
    -1.59
    amp
    -1.54
     itself
    -1.52
     Industry
    -1.42
    aling
    -1.40
    itting
    -1.37
    "?"
    -1.36
    las
    -1.34
    POSITIVE LOGITS
    ville
    1.83
    bank
    1.60
    grade
    1.53
    iero
    1.53
    quilibrium
    1.50
    iances
    1.46
     pronounce
    1.45
    strom
    1.44
    ģ
    1.42
    bles
    1.40
    Activations Density 0.033%

    No Known Activations