© 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. 24518
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their structural components

    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
    482
    +0.12
    0.7%
    159
    +0.12
    0.7%
    109
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.12
    0.04
    109
    +0.12
    0.05
    322
    +0.11
    0.04
    Negative Logits
    )),
    -1.58
    ));
    -1.56
     sizes
    -1.51
    ))$.
    -1.51
     ))
    -1.50
    )).
    -1.49
    ))\
    -1.47
     footer
    -1.44
    ameter
    -1.43
    )));
    -1.42
    POSITIVE LOGITS
    ³
    2.58
    ±
    2.36
    ŀ
    2.30
    Ł
    2.15
    ļ
    2.14
    İ
    2.08
    Ļª
    2.08
    Ļ
    2.06
    Ĵ
    2.04
    Ī
    2.04
    Activations Density 0.131%

    No Known Activations