© 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. 28703
    Prev
    Next
    INDEX
    Explanations

    documents related to government policies or legal acts

    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
    346
    +0.14
    0.8%
    462
    +0.13
    0.8%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.14
    0.11
    36
    +0.13
    0.09
    280
    +0.12
    0.08
    Negative Logits
    ureus
    -2.01
    \[[@
    -1.67
    uro
    -1.67
    ource
    -1.49
    «
    -1.48
    buffered
    -1.48
     Bangladesh
    -1.46
    Ł
    -1.43
    vens
    -1.42
    ĨĴ
    -1.41
    POSITIVE LOGITS
     interest
    1.69
     tips
    1.56
     prayers
    1.54
     dream
    1.51
     advice
    1.50
     appointment
    1.49
     innocence
    1.45
     extraordinary
    1.43
     pointers
    1.43
     encouragement
    1.41
    Activations Density 0.136%

    No Known Activations