© 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. 26160
    Prev
    Next
    INDEX
    Explanations

    references to a specific character encoding standard

    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
    320
    +0.15
    0.9%
    111
    +0.15
    0.9%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    169
    +0.15
    0.01
    199
    +0.12
    0.01
    Negative Logits
    ¿
    -2.60
    į
    -2.37
    «
    -2.35
    Īĺ
    -2.34
    ı
    -2.29
    ·¸
    -2.27
    ¿½
    -2.25
    Ĺ
    -2.20
    ľĵ
    -2.15
    ĥ
    -2.13
    POSITIVE LOGITS
    nai
    1.97
    lä
    1.95
    agne
    1.85
    fors
    1.76
    för
    1.74
    chester
    1.73
    áĢ¬
    1.72
    krit
    1.68
    ű
    1.67
    skins
    1.66
    Activations Density 0.187%

    No Known Activations