© 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. 25909
    Prev
    Next
    INDEX
    Explanations

    words associated with authority figures or leadership roles

    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
    219
    +0.12
    0.7%
    362
    +0.11
    0.6%
    364
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.12
    0.01
    438
    +0.11
    0.01
    442
    +0.10
    0.02
    Negative Logits
    "?"
    -1.96
    ANE
    -1.78
    aned
    -1.77
     ?"
    -1.76
    '?"
    -1.72
     thee
    -1.66
    ..."
    -1.60
     value
    -1.59
     ."
    -1.59
     MERCHANTABILITY
    -1.58
    POSITIVE LOGITS
    ħ
    2.01
    ship
    1.87
    ©
    1.83
    ģ
    1.82
    bilt
    1.80
    ª
    1.80
    ships
    1.79
    ium
    1.76
    ström
    1.75
    holm
    1.71
    Activations Density 4.704%

    No Known Activations