© 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. 29661
    Prev
    Next
    INDEX
    Explanations

    references to annotations and the process of annotating

    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
    156
    +0.17
    1.0%
    376
    +0.17
    1.0%
    217
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.17
    0.01
    178
    +0.17
    0.01
    156
    +0.12
    0.01
    Negative Logits
    ĥ½
    -3.27
    »¿
    -2.75
    ı
    -2.63
    Ļª
    -2.50
    ĵ
    -2.42
    ħ
    -2.38
    Į
    -2.37
    ĥ
    -2.35
    ¯
    -2.31
    ĺ
    -2.31
    POSITIVE LOGITS
     area
    1.67
     era
    1.66
    ist
    1.61
    naire
    1.60
    veolar
    1.60
    ese
    1.54
    feit
    1.54
     purposes
    1.53
    cias
    1.50
     arts
    1.49
    Activations Density 0.017%

    No Known Activations