© 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. 24585
    Prev
    Next
    INDEX
    Explanations

    references to the programming language Dart

    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
    23
    +0.17
    0.9%
    454
    +0.12
    0.7%
    378
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.04
    332
    +0.12
    0.04
    232
    +0.12
    0.04
    Negative Logits
    .).
    -1.65
    aires
    -1.64
     campaign
    -1.58
     âĨĴ
    -1.46
    taire
    -1.45
     nr
    -1.45
    ÅĽci
    -1.43
     nearer
    -1.42
    olta
    -1.41
     strateg
    -1.40
    POSITIVE LOGITS
    °
    3.56
    ĻĤ
    3.35
    Īĺ
    3.26
    ĺ
    3.18
    ¿½
    3.17
    ľĵ
    3.13
    Ł
    3.04
    ķ
    3.02
    ľ
    3.02
    ij
    2.98
    Activations Density 0.510%

    No Known Activations