© 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. 2-MLP-SM
    11. 24907
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or expressions related to systems or functions

    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
    156
    +0.33
    1.9%
    386
    +0.15
    0.9%
    472
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.33
    0.02
    56
    +0.15
    0.03
    313
    +0.13
    0.01
    Negative Logits
    Īĺ
    -2.26
    č↵
    -2.13
    -2.13
    ↵
    -2.13
    ↵↵
    -2.13
    ↵
    -2.13
    ↵
    -2.13
                  ↵
    -2.13
    -2.13
    -2.13
    POSITIVE LOGITS
    aki
    1.58
    while
    1.49
    aka
    1.46
    IES
    1.37
    our
    1.34
     creation
    1.33
     we
    1.31
    producing
    1.31
     teac
    1.31
    ressing
    1.31
    Activations Density 0.197%

    No Known Activations