© 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 EvalsExportsAPI 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. 28497
    Prev
    Next
    INDEX
    Explanations

    specific Java or programming-related exceptions and identifiers

    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
    256
    +0.13
    0.7%
    417
    +0.12
    0.7%
    412
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.13
    0.03
    369
    +0.12
    0.03
    301
    +0.11
    0.03
    Negative Logits
    imeter
    -1.73
    terday
    -1.67
     nausea
    -1.65
    ibilities
    -1.64
     laughter
    -1.63
     smile
    -1.60
    ¿½
    -1.60
     deaf
    -1.59
    Īĺ
    -1.59
     hesitate
    -1.58
    POSITIVE LOGITS
    CC
    2.04
    aps
    1.98
    DL
    1.96
    BD
    1.94
    PL
    1.91
    PI
    1.91
    dp
    1.88
    CP
    1.86
    BA
    1.86
    DP
    1.81
    Activations Density 3.019%

    No Known Activations