© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23554
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing simplicity and clarity in expressions

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.17
    1.0%
    303
    +0.16
    0.9%
    342
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.17
    0.08
    147
    +0.16
    0.05
    500
    +0.14
    0.03
    Negative Logits
    Ļª
    -3.65
    į
    -3.37
    ļ
    -3.23
    ĨĴ
    -3.23
    Ģ
    -3.15
    ¼
    -3.15
    ħ
    -3.11
    ł
    -3.02
    ¡
    -3.00
    ĻĤ
    -2.96
    POSITIVE LOGITS
    ged
    1.58
    omitempty
    1.52
    rake
    1.51
     anything
    1.47
     completion
    1.45
     complete
    1.43
     optimum
    1.42
    ally
    1.41
    idth
    1.36
    emale
    1.35
    Activations Density 0.740%

    No Known Activations