© 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. 26219
    Prev
    Next
    INDEX
    Explanations

    elements of code and programming structures

    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
    179
    +0.14
    0.8%
    86
    +0.12
    0.7%
    88
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.14
    0.11
    371
    +0.12
    0.12
    188
    +0.11
    0.09
    Negative Logits
    raft
    -1.73
     outlet
    -1.54
    estock
    -1.50
    heart
    -1.45
     hundred
    -1.31
    eness
    -1.29
     hourly
    -1.27
    past
    -1.27
     herds
    -1.27
     cows
    -1.26
    POSITIVE LOGITS
    °
    3.03
    ¯
    2.39
    ±
    2.38
    ¡
    2.33
    ħ
    2.23
    Ļ
    2.22
    Ń
    2.22
    ŀ
    2.20
    į
    2.18
    µ
    2.15
    Activations Density 3.649%

    No Known Activations