© 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. 30160
    Prev
    Next
    INDEX
    Explanations

    structured data elements or components in code

    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
    478
    +0.15
    0.8%
    130
    +0.13
    0.7%
    298
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.15
    0.01
    130
    +0.13
    0.01
    417
    +0.12
    0.01
    Negative Logits
    ħ
    -1.91
     physicist
    -1.57
    fessor
    -1.55
    ings
    -1.50
    .]{}
    -1.47
    ista
    -1.46
     ([
    -1.46
    hematic
    -1.45
    emaker
    -1.45
    ESE
    -1.44
    POSITIVE LOGITS
    ť
    1.61
     validity
    1.56
    ween
    1.51
     "âĻª
    1.47
    Alignment
    1.40
    dfrac
    1.39
    nolimits
    1.37
    rele
    1.34
    Justice
    1.34
    valued
    1.33
    Activations Density 0.024%

    No Known Activations