© 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. 29325
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical elements and compounds, particularly potassium and ammonium

    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
    1.1%
    71
    +0.13
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.18
    0.01
    111
    +0.13
    0.01
    320
    +0.12
    0.01
    Negative Logits
    orems
    -2.04
    ij
    -1.81
    raints
    -1.79
    ľ
    -1.78
    rapeut
    -1.71
    Ŀ
    -1.68
     lieu
    -1.61
    Ĭ
    -1.60
    cca
    -1.59
    yles
    -1.51
    POSITIVE LOGITS
     depends
    1.60
    eral
    1.60
    istani
    1.52
    /~
    1.50
     crore
    1.50
    /.
    1.49
    erals
    1.49
     (@
    1.48
    heet
    1.44
     sucks
    1.44
    Activations Density 0.005%

    No Known Activations