© 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. 29646
    Prev
    Next
    INDEX
    Explanations

    substantial numeric values or terms related to quantifiable measurements

    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
    35
    +0.12
    0.7%
    340
    +0.12
    0.6%
    112
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.33
    23
    +0.12
    0.29
    494
    +0.12
    0.23
    Negative Logits
    fully
    -1.79
    ontally
    -1.70
    lessly
    -1.68
    ?)
    -1.60
    ect
    -1.51
    -,
    -1.49
    -)
    -1.37
    ures
    -1.36
    aft
    -1.33
    ified
    -1.33
    POSITIVE LOGITS
    zza
    1.69
    iencies
    1.57
     Briefly
    1.57
    xiv
    1.56
    cknowled
    1.52
    1371
    1.46
     else
    1.45
    ruz
    1.40
    enza
    1.39
    ITY
    1.37
    Activations Density 3.161%

    No Known Activations