© 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. 25278
    Prev
    Next
    INDEX
    Explanations

    references to specific software versions or related digital artifacts

    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
    +0.34
    1.9%
    417
    +0.11
    0.6%
    23
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.34
    0.04
    325
    +0.11
    0.03
    97
    +0.11
    0.02
    Negative Logits
    ĥ½
    -2.57
    Ħ
    -2.17
    ĻĤ
    -2.16
    ĸ´
    -2.16
              ↵
    -2.09
    č↵
    -2.09
    č↵
    -2.09
    -2.09
    ↵
    -2.09
    ↵↵↵
    -2.09
    POSITIVE LOGITS
     stranger
    1.52
    dirname
    1.35
    ‘
    1.35
     LLP
    1.35
    inous
    1.34
    shots
    1.33
     filmed
    1.31
     recorded
    1.31
     sharp
    1.30
     scattering
    1.30
    Activations Density 0.222%

    No Known Activations