© 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. 26708
    Prev
    Next
    INDEX
    Explanations

    mentions of system-related concepts and commands

    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
    376
    +0.13
    0.7%
    240
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.13
    0.01
    158
    +0.12
    0.01
    320
    +0.12
    0.01
    Negative Logits
    zier
    -1.73
    |$.
    -1.59
    atosis
    -1.55
    eds
    -1.51
    anu
    -1.49
    ations
    -1.45
    eping
    -1.42
    ation
    -1.39
    ĥ
    -1.39
    alus
    -1.38
    POSITIVE LOGITS
     embodiment
    1.61
    istical
    1.57
     excuse
    1.55
    ematic
    1.51
    ingly
    1.46
     era
    1.45
    coin
    1.43
    thy
    1.39
    raged
    1.37
     attitude
    1.37
    Activations Density 0.049%

    No Known Activations