© 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. 23046
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to decision-making processes and evaluations

    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
    145
    +0.16
    0.9%
    437
    +0.11
    0.6%
    453
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.16
    0.04
    453
    +0.11
    0.03
    37
    +0.11
    0.03
    Negative Logits
    References
    -1.50
     momentum
    -1.49
    onym
    -1.45
    Ļª
    -1.44
    ↵
    -1.38
    ↵
    -1.38
    -1.38
    -1.38
     ↵
    -1.38
     ↵
    -1.38
    POSITIVE LOGITS
    boats
    1.73
    helm
    1.64
    joy
    1.58
    acio
    1.55
    aho
    1.55
    obo
    1.55
     boats
    1.54
    urers
    1.54
    bay
    1.50
    lio
    1.49
    Activations Density 0.064%

    No Known Activations