© 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. 23389
    Prev
    Next
    INDEX
    Explanations

    phrases related to research and academic studies

    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
    97
    +0.14
    0.8%
    388
    +0.11
    0.6%
    508
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.14
    0.03
    380
    +0.11
    0.02
    508
    +0.11
    0.03
    Negative Logits
    Ĵ
    -2.02
    Īĺ
    -1.98
    ı
    -1.96
    ↵  ³³³
    -1.87
    -1.87
    -1.87
    ↵
    -1.87
    ↵↵
    -1.87
    -1.87
    -1.87
    POSITIVE LOGITS
    ÃŃc
    1.91
    isd
    1.81
     dass
    1.73
    zet
    1.70
    ções
    1.62
    sx
    1.60
    ert
    1.51
    ipt
    1.51
     punches
    1.49
    ases
    1.46
    Activations Density 0.345%

    No Known Activations