© 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. 2-MLP-SM
    11. 22770
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce conditions or exceptions

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    439
    +0.14
    0.8%
    95
    +0.11
    0.6%
    292
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.14
    0.14
    412
    +0.11
    0.13
    407
    +0.11
    0.13
    Negative Logits
    ©
    -3.43
    ĻĤ
    -3.13
    ³
    -3.13
    °
    -2.98
    ¿½
    -2.94
    ł
    -2.83
    ·¸
    -2.80
    ¤
    -2.79
    ±
    -2.77
    ¨
    -2.75
    POSITIVE LOGITS
     doubles
    1.56
    née
    1.47
    rael
    1.44
    roads
    1.43
    plots
    1.41
    /
    1.41
     abroad
    1.40
    ours
    1.40
    ,\[
    1.39
    ometers
    1.37
    Activations Density 0.913%

    No Known Activations