© 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. 2-MLP-SM
    11. 22453
    Prev
    Next
    INDEX
    Explanations

    the possessive pronoun "whose"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    176
    +0.12
    0.7%
    255
    +0.12
    0.7%
    426
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.12
    0.02
    255
    +0.12
    0.03
    461
    +0.11
    0.03
    Negative Logits
     breeze
    -1.64
     thinner
    -1.63
     increments
    -1.52
     mild
    -1.46
     neut
    -1.42
     puck
    -1.42
     sunlight
    -1.41
     bend
    -1.39
     thicker
    -1.38
     hurry
    -1.36
    POSITIVE LOGITS
    forge
    1.75
    IJ
    1.71
    ĥ½
    1.70
    ugu
    1.70
    ®
    1.65
    úblic
    1.65
    xico
    1.61
    ĥ
    1.60
    »
    1.53
    vision
    1.50
    Activations Density 0.149%

    No Known Activations