© 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. 27024
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the combination or integration of elements or ideas

    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
    376
    +0.23
    1.3%
    316
    +0.11
    0.6%
    32
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.23
    0.01
    62
    +0.11
    0.01
    94
    +0.11
    0.01
    Negative Logits
    shire
    -1.79
    liche
    -1.56
    ll
    -1.45
    ledge
    -1.44
    liver
    -1.43
    uten
    -1.43
    llo
    -1.42
    HS
    -1.40
    ska
    -1.38
    ted
    -1.35
    POSITIVE LOGITS
    Īĺ
    2.67
    chitz
    1.96
    ·
    1.95
    ¢
    1.89
    £
    1.88
    ĸ´
    1.87
    ¿
    1.79
    Ĺ
    1.75
    ¨
    1.74
    oelectric
    1.72
    Activations Density 0.021%

    No Known Activations