© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23931
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "current."

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    231
    +0.11
    0.6%
    368
    +0.10
    0.6%
    487
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.11
    0.03
    325
    +0.10
    0.02
    179
    +0.10
    0.02
    Negative Logits
     vote
    -1.49
    Listener
    -1.47
     breeze
    -1.45
    TOF
    -1.44
    Event
    -1.37
    $^{
    -1.37
    iratory
    -1.37
    onium
    -1.36
     detectors
    -1.35
    jo
    -1.35
    POSITIVE LOGITS
    aji
    1.63
    resse
    1.53
    ி
    1.50
    stitute
    1.48
    ritis
    1.38
    ungal
    1.37
     Estate
    1.36
     estate
    1.35
    à¯
    1.34
    ftware
    1.33
    Activations Density 0.102%

    No Known Activations