© 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. 22503
    Prev
    Next
    INDEX
    Explanations

    apostrophes and quotation marks in various contexts

    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
    264
    +0.13
    0.7%
    419
    +0.12
    0.7%
    176
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.13
    0.04
    419
    +0.12
    0.03
    56
    +0.12
    0.05
    Negative Logits
     himself
    -1.77
    ylated
    -1.55
    Ľ
    -1.47
    alian
    -1.46
     herself
    -1.46
     yourself
    -1.45
    olin
    -1.44
     trainer
    -1.41
    LY
    -1.39
     sich
    -1.38
    POSITIVE LOGITS
    ear
    1.69
    elon
    1.62
    im
    1.53
    .")
    1.50
    "))
    1.49
    STEM
    1.48
    .](
    1.46
     ](
    1.44
    .").
    1.42
    ëĭĪëĭ¤
    1.42
    Activations Density 0.179%

    No Known Activations