© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25273
    Prev
    Next
    INDEX
    Explanations

    references to the logical operator "OR"

    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
    300
    +0.13
    0.8%
    369
    +0.11
    0.7%
    134
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.13
    0.03
    134
    +0.11
    0.03
    159
    +0.10
    0.03
    Negative Logits
    ching
    -1.87
    hern
    -1.53
    rying
    -1.53
    awning
    -1.52
    anning
    -1.48
    upon
    -1.44
     reply
    -1.43
    "?
    -1.42
     Honorable
    -1.42
    aning
    -1.39
    POSITIVE LOGITS
    GAN
    1.84
    ptions
    1.80
    enos
    1.75
    ista
    1.72
    ées
    1.70
    enez
    1.68
    blic
    1.67
    ÃŃf
    1.61
    bic
    1.59
    ifice
    1.59
    Activations Density 0.120%

    No Known Activations