© 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. 23181
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations in England

    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
    72
    +0.11
    0.6%
    23
    +0.11
    0.6%
    359
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.11
    0.03
    344
    +0.11
    0.04
    194
    +0.11
    0.04
    Negative Logits
    izes
    -1.73
    ETHOD
    -1.65
    ialize
    -1.64
     forums
    -1.64
    ocs
    -1.64
    icolor
    -1.62
    aves
    -1.62
     apparatus
    -1.56
    \]](
    -1.52
    EXPORT
    -1.50
    POSITIVE LOGITS
    ł
    1.73
    ¸
    1.70
    ittle
    1.58
    leigh
    1.52
     Mah
    1.45
     Thai
    1.42
     Wellington
    1.40
    äsident
    1.40
    rolling
    1.35
    ¤
    1.35
    Activations Density 0.275%

    No Known Activations