© 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 EvalsExportsAPI 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. 29209
    Prev
    Next
    INDEX
    Explanations

    references to Britain

    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
    +0.14
    0.8%
    377
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.14
    0.02
    382
    +0.12
    0.01
    389
    +0.12
    0.01
    Negative Logits
     scheduled
    -1.59
    ounder
    -1.50
    qq
    -1.50
    idered
    -1.46
     serving
    -1.46
    quired
    -1.44
     lasting
    -1.41
    ked
    -1.40
    ras
    -1.39
     Jama
    -1.37
    POSITIVE LOGITS
    sheet
    1.75
    liography
    1.74
    encial
    1.72
    genstein
    1.71
     herself
    1.69
    àµį
    1.61
    \$
    1.59
    enstein
    1.58
     Clerk
    1.56
    ophone
    1.54
    Activations Density 0.397%

    No Known Activations