© 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. 28569
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of uncertainty or curiosity

    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
    75
    +0.12
    0.7%
    410
    +0.12
    0.7%
    214
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.01
    366
    +0.12
    0.01
    309
    +0.11
    0.01
    Negative Logits
     ?"
    -1.79
     METHODS
    -1.68
     ");
    -1.66
    aning
    -1.57
    ishing
    -1.55
     ")
    -1.53
     reviewed
    -1.50
    ances
    -1.47
    itoring
    -1.42
    .")
    -1.41
    POSITIVE LOGITS
    ·
    2.70
    ĻĤ
    2.35
    į
    2.28
    Į
    2.22
    ½
    2.19
    £
    2.17
    ¤
    2.11
    ģ
    2.10
    ī
    2.09
    ŀ
    2.09
    Activations Density 0.092%

    No Known Activations