© 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. 24083
    Prev
    Next
    INDEX
    Explanations

    references to software licenses

    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
    345
    +0.15
    0.8%
    156
    +0.13
    0.7%
    386
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.15
    0.04
    495
    +0.13
    0.04
    424
    +0.13
    0.03
    Negative Logits
    ()));
    -1.95
    "));
    -1.93
    ”).
    -1.89
    '));
    -1.87
    '))
    -1.79
    ”),
    -1.71
     effect
    -1.70
    ));
    -1.60
    )).
    -1.60
    ").
    -1.59
    POSITIVE LOGITS
    ģ
    2.44
    ĵ
    2.18
    ±
    2.16
    ª
    2.03
    mie
    2.03
    §
    2.03
    Ļ
    2.00
    ĭ
    1.96
    Ľ
    1.95
    ĥ
    1.87
    Activations Density 0.072%

    No Known Activations