© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 27062
    Prev
    Next
    INDEX
    Explanations

    references to Japan and its cultural or societal aspects

    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
    141
    +0.13
    0.7%
    142
    +0.13
    0.7%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.13
    0.04
    311
    +0.13
    0.03
    9
    +0.12
    0.04
    Negative Logits
    ·¸
    -1.55
    Populated
    -1.55
    ļ
    -1.55
     chambers
    -1.51
    argin
    -1.50
    avian
    -1.49
    ı
    -1.48
    £
    -1.42
    à±
    -1.40
    ubern
    -1.37
    POSITIVE LOGITS
    plings
    1.75
     Rs
    1.56
     heed
    1.51
     CAG
    1.49
     along
    1.49
    enge
    1.48
    ages
    1.44
    greg
    1.44
    ato
    1.43
     Tet
    1.41
    Activations Density 0.395%

    No Known Activations