© 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. 25783
    Prev
    Next
    INDEX
    Explanations

    indicators of important numerical or statistical data

    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
    369
    +0.18
    1.0%
    502
    +0.15
    0.8%
    397
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.18
    0.03
    502
    +0.15
    0.04
    415
    +0.14
    0.03
    Negative Logits
    resis
    -1.98
    xtures
    -1.85
    keit
    -1.85
    xture
    -1.83
    oise
    -1.75
     forma
    -1.70
    >()
    -1.66
     invention
    -1.60
    herty
    -1.56
    ção
    -1.51
    POSITIVE LOGITS
     than
    1.77
    aspberry
    1.57
     speaking
    1.56
     requiring
    1.53
    culus
    1.49
    onda
    1.46
     dating
    1.43
     supported
    1.41
    ismatic
    1.41
     founded
    1.39
    Activations Density 0.016%

    No Known Activations