© 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. 2-MLP-SM
    11. 23630
    Prev
    Next
    INDEX
    Explanations

    phrases related to licenses and legal permissions

    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
    178
    +0.18
    1.0%
    500
    +0.13
    0.7%
    123
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.18
    0.08
    123
    +0.13
    0.05
    407
    +0.12
    0.07
    Negative Logits
    reen
    -1.83
    mer
    -1.66
    journal
    -1.56
    teenth
    -1.54
     page
    -1.43
    der
    -1.42
    weg
    -1.42
    ORS
    -1.42
    ield
    -1.40
    gels
    -1.39
    POSITIVE LOGITS
    ypse
    1.79
     disturbances
    1.58
    ”.
    1.55
    *](#
    1.55
    Ļª
    1.51
     sparing
    1.50
     fold
    1.47
    Inflater
    1.44
    dala
    1.44
    âĭ¯
    1.44
    Activations Density 0.392%

    No Known Activations