© 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. 23573
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and jurisdictional information

    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
    156
    +0.15
    0.8%
    313
    +0.12
    0.7%
    197
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.15
    0.09
    298
    +0.12
    0.10
    79
    +0.11
    0.09
    Negative Logits
    zona
    -2.03
    esian
    -1.74
     ([@
    -1.72
    iday
    -1.70
    usiness
    -1.63
     âĢķ
    -1.61
    isure
    -1.60
    ijan
    -1.51
    license
    -1.49
    htra
    -1.49
    POSITIVE LOGITS
    ¼
    1.88
    «
    1.67
     hands
    1.64
    ¾
    1.59
    Ĭ
    1.59
    ³
    1.57
    ī
    1.54
    ´
    1.46
    ĻĤ
    1.45
    Ł
    1.42
    Activations Density 1.924%

    No Known Activations