© 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. 28559
    Prev
    Next
    INDEX
    Explanations

    sections marked as "Discussion" or "Ground."

    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
    389
    +0.13
    0.8%
    71
    +0.12
    0.7%
    39
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.13
    0.01
    389
    +0.12
    0.01
    205
    +0.12
    0.01
    Negative Logits
    onin
    -1.60
    dess
    -1.47
    bs
    -1.39
     thanked
    -1.38
    augh
    -1.33
    arte
    -1.33
    fort
    -1.33
    twitter
    -1.32
    pling
    -1.31
     daÃŁ
    -1.31
    POSITIVE LOGITS
    ¢
    2.25
    £
    2.25
    Ļª
    2.16
    ¡
    1.96
    ģ
    1.94
    ¥
    1.92
    ŀ
    1.91
    «
    1.76
    ª
    1.63
    Ĺ
    1.63
    Activations Density 1.679%

    No Known Activations