© 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. 29203
    Prev
    Next
    INDEX
    Explanations

    the word "Car."

    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
    457
    +0.13
    0.7%
    410
    +0.10
    0.6%
    485
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.01
    194
    +0.10
    0.01
    363
    +0.10
    0.01
    Negative Logits
    ĥ½
    -3.50
    Ĥ¬
    -3.17
    Ĥ
    -3.02
    Ń
    -3.01
    ĸ´
    -2.99
    ¹
    -2.96
    Ĭ
    -2.92
    ¶
    -2.90
    ĥ
    -2.88
    ĩ
    -2.87
    POSITIVE LOGITS
    pool
    1.97
    illon
    1.94
    nor
    1.79
    abine
    1.72
    ist
    1.62
    ib
    1.60
    ousel
    1.57
    bridge
    1.55
    ious
    1.54
    bank
    1.52
    Activations Density 0.045%

    No Known Activations