© 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. 26793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intent or directionality

    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
    350
    +0.13
    0.7%
    221
    +0.12
    0.7%
    258
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.38
    151
    +0.12
    0.31
    434
    +0.12
    0.31
    Negative Logits
     known
    -1.48
    ics
    -1.41
    ea
    -1.41
    umab
    -1.40
    nas
    -1.38
     invasion
    -1.35
    oplan
    -1.32
    Ī
    -1.30
    aurus
    -1.29
    called
    -1.29
    POSITIVE LOGITS
    ż
    1.70
    urally
    1.52
     constraints
    1.41
    assen
    1.38
    FFER
    1.38
     oversight
    1.38
    ily
    1.37
     lieu
    1.36
     figure
    1.36
     parentheses
    1.34
    Activations Density 1.659%

    No Known Activations