© 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. 0-MLP-SM
    11. 26048
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thanks

    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
    +0.15
    0.8%
    366
    +0.12
    0.7%
    334
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.15
    0.03
    334
    +0.12
    0.02
    138
    +0.12
    0.02
    Negative Logits
     Edit
    -1.37
     Cele
    -1.36
     Cape
    -1.34
     cele
    -1.32
    [/
    -1.32
     Antar
    -1.31
     Spiel
    -1.27
     tabs
    -1.27
     slots
    -1.27
     competitors
    -1.24
    POSITIVE LOGITS
    ¥
    2.10
    ľĵ
    2.07
    fully
    1.96
    ł
    1.92
    ĥ
    1.87
    ģ
    1.83
    »¿
    1.80
    ¢
    1.79
    ±
    1.78
    ful
    1.73
    Activations Density 0.087%

    No Known Activations