© 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. 29502
    Prev
    Next
    INDEX
    Explanations

    references to Melbourne

    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
    +0.20
    1.2%
    182
    +0.16
    1.0%
    71
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.20
    0.02
    71
    +0.16
    0.02
    80
    +0.16
    0.02
    Negative Logits
    ages
    -1.79
     ours
    -1.78
    usterity
    -1.76
     yours
    -1.68
     anonymity
    -1.52
     hers
    -1.45
     his
    -1.43
     worse
    -1.43
    wd
    -1.37
    ONS
    -1.36
    POSITIVE LOGITS
    vist
    2.00
    àµį
    1.88
    à±į
    1.86
    àµ
    1.83
    ycin
    1.74
    à±ģ
    1.73
     outlet
    1.72
    ி
    1.69
    bolt
    1.62
    ian
    1.61
    Activations Density 0.016%

    No Known Activations