© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28309
    Prev
    Next
    INDEX
    Explanations

    mentions of protests and related actions

    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
    156
    +0.28
    1.7%
    115
    +0.14
    0.8%
    72
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.28
    0.01
    266
    +0.14
    0.01
    156
    +0.12
    0.01
    Negative Logits
    shore
    -1.60
    IFE
    -1.57
    AndroidRuntime
    -1.56
     Publ
    -1.55
    ferential
    -1.54
    Copyright
    -1.54
    inx
    -1.52
     vivo
    -1.51
    heets
    -1.48
    fasterxml
    -1.47
    POSITIVE LOGITS
     complaints
    1.74
    lass
    1.73
    birds
    1.72
     styles
    1.61
     festivals
    1.59
     movements
    1.57
    imeters
    1.51
    ging
    1.46
     proposals
    1.44
    ist
    1.43
    Activations Density 0.024%

    No Known Activations