© 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. 28355
    Prev
    Next
    INDEX
    Explanations

    references to short documents or brief texts

    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
    362
    +0.10
    0.6%
    496
    +0.10
    0.6%
    253
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.10
    0.04
    198
    +0.10
    0.03
    288
    +0.10
    0.03
    Negative Logits
    aff
    -1.69
    ocyan
    -1.54
    asc
    -1.51
    ucc
    -1.48
    odi
    -1.46
    osc
    -1.42
     fully
    -1.41
    onas
    -1.40
     appropriate
    -1.38
    izoph
    -1.35
    POSITIVE LOGITS
    falls
    2.24
    listed
    1.88
    ableness
    1.85
    heid
    1.80
    itud
    1.80
    cake
    1.79
     ago
    1.77
    coming
    1.70
    burg
    1.70
    kered
    1.62
    Activations Density 0.197%

    No Known Activations