© 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. 25317
    Prev
    Next
    INDEX
    Explanations

    instances of the word "experiment."

    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
    156
    +0.21
    1.2%
    212
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.21
    0.02
    343
    +0.12
    0.01
    14
    +0.11
    0.01
    Negative Logits
    ¯
    -2.11
    ĨĴ
    -1.92
    ĥ½
    -1.84
    §
    -1.77
     majority
    -1.70
    ¿
    -1.66
    zzo
    -1.61
    »
    -1.59
    Ļª
    -1.57
    cu
    -1.54
    POSITIVE LOGITS
    grounds
    1.84
    icle
    1.77
    emaker
    1.64
    emis
    1.60
    avis
    1.59
    ground
    1.55
    esy
    1.54
    ade
    1.53
    iem
    1.53
    eral
    1.52
    Activations Density 0.006%

    No Known Activations