© 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. 2-MLP-SM
    11. 25332
    Prev
    Next
    INDEX
    Explanations

    references to advocacy and non-profit organizations

    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
    90
    +0.15
    0.9%
    162
    +0.13
    0.8%
    306
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.15
    0.14
    60
    +0.13
    0.05
    306
    +0.12
    0.08
    Negative Logits
    Ļª
    -2.79
    ľĵ
    -2.40
    IJ
    -2.33
    ĨĴ
    -2.23
    Ĺ
    -2.10
    ľ
    -2.02
    Ģ
    -1.99
    Į
    -1.98
    ª
    -1.96
    ł
    -1.94
    POSITIVE LOGITS
    nier
    1.59
     Caption
    1.43
    baum
    1.43
     год
    1.32
     âĢķ
    1.29
    bridge
    1.28
     --
    1.27
     auction
    1.26
    aurus
    1.26
     Web
    1.22
    Activations Density 1.985%

    No Known Activations