© 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. 24265
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of reduction or minimizing negative impacts

    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
    118
    +0.16
    0.9%
    358
    +0.12
    0.7%
    404
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.16
    0.04
    404
    +0.12
    0.04
    362
    +0.11
    0.03
    Negative Logits
    AMS
    -1.60
     notice
    -1.50
    ĥ
    -1.47
    ches
    -1.41
    IR
    -1.41
     BGCOLOR
    -1.41
     caution
    -1.39
    irm
    -1.38
    ITE
    -1.37
    ACE
    -1.35
    POSITIVE LOGITS
    liga
    1.55
     runway
    1.53
    DLT
    1.49
    starter
    1.47
    blic
    1.47
    née
    1.47
    stairs
    1.45
    jsfiddle
    1.43
    ène
    1.41
    rette
    1.41
    Activations Density 0.214%

    No Known Activations