© 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. 30632
    Prev
    Next
    INDEX
    Explanations

    instances of the word "could" indicating potential or possibility

    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
    351
    +0.14
    0.8%
    10
    +0.14
    0.8%
    237
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.14
    0.10
    486
    +0.14
    0.08
    415
    +0.12
    0.07
    Negative Logits
    ŀ
    -2.05
    Ĭ
    -2.02
    ¸
    -1.95
    £
    -1.92
    ©
    -1.85
    ĸ
    -1.84
    ¡
    -1.81
    Ķ
    -1.79
    Īĺ
    -1.77
    ij
    -1.75
    POSITIVE LOGITS
    ega
    1.73
    rene
    1.68
    roup
    1.64
    asio
    1.50
    rena
    1.48
     ![](
    1.45
    ictional
    1.42
    onica
    1.41
    orphism
    1.39
    .";
    1.38
    Activations Density 0.061%

    No Known Activations