© 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. 25527
    Prev
    Next
    INDEX
    Explanations

    references to insurance-related terms and concepts

    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
    +0.18
    1.1%
    2
    +0.11
    0.6%
    375
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.18
    0.03
    143
    +0.11
    0.03
    333
    +0.11
    0.03
    Negative Logits
    ¿
    -2.00
    Ŀ
    -1.98
    ¯
    -1.98
    IJ
    -1.96
    ĥ½
    -1.96
    ľ
    -1.93
    ±
    -1.84
    Ģ
    -1.80
    ĥ
    -1.71
    ¹
    -1.69
    POSITIVE LOGITS
    ume
    1.76
    CTX
    1.74
    control
    1.70
    yard
    1.70
    factor
    1.69
    eed
    1.59
    circuit
    1.54
    eno
    1.52
    "}](#
    1.50
    markets
    1.50
    Activations Density 0.028%

    No Known Activations