© 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. 29207
    Prev
    Next
    INDEX
    Explanations

    instances of centered text formatting

    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
    193
    +0.15
    0.9%
    29
    +0.11
    0.7%
    385
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.15
    0.22
    310
    +0.11
    0.19
    217
    +0.11
    0.17
    Negative Logits
    LLOW
    -1.77
     pleasure
    -1.76
    ytes
    -1.74
    ¦
    -1.70
    ĨĴ
    -1.68
     APPEALS
    -1.65
    ¿½
    -1.63
    ellow
    -1.62
    §
    -1.61
     fancy
    -1.56
    POSITIVE LOGITS
    piece
    2.37
    pieces
    2.24
    ière
    1.95
    kok
    1.92
    work
    1.87
    yard
    1.83
    borg
    1.81
    grounds
    1.79
    pool
    1.77
    liga
    1.75
    Activations Density 0.925%

    No Known Activations