© 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. 27085
    Prev
    Next
    INDEX
    Explanations

    instances of the word "removed."

    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
    +0.24
    1.4%
    115
    +0.13
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.24
    0.02
    474
    +0.13
    0.02
    308
    +0.12
    0.02
    Negative Logits
    ĵ
    -2.66
    ĥ
    -2.51
    Ī
    -2.50
    ĨĴ
    -2.43
    ĥ½
    -2.33
    ķ
    -2.32
    »¿
    -2.27
    Ĵ
    -2.26
    Īĺ
    -2.25
    ı
    -2.21
    POSITIVE LOGITS
     ones
    1.47
     @@
    1.42
     impurities
    1.41
    enging
    1.38
     sins
    1.33
    sect
    1.31
    plement
    1.30
    omit
    1.29
     positions
    1.28
    iating
    1.27
    Activations Density 0.023%

    No Known Activations