© 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. 29012
    Prev
    Next
    INDEX
    Explanations

    phrases involving the concept of "of" indicating possession, association, or classification

    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
    23
    +0.16
    0.9%
    198
    +0.12
    0.7%
    116
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.16
    0.26
    136
    +0.12
    0.23
    225
    +0.11
    0.23
    Negative Logits
    §
    -2.19
    ģ
    -1.91
    Ń
    -1.87
    ¨
    -1.85
    culos
    -1.81
    ¤
    -1.78
    umni
    -1.78
    ī
    -1.77
    ĥ
    -1.76
    ĩ
    -1.75
    POSITIVE LOGITS
    iveness
    1.71
    hip
    1.56
    ence
    1.54
     chance
    1.54
     footing
    1.52
    ened
    1.52
    ioned
    1.51
     mercy
    1.48
    ening
    1.47
     {@
    1.45
    Activations Density 1.533%

    No Known Activations