© 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. 31224
    Prev
    Next
    INDEX
    Explanations

    phrases related to identification and assessment

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.20
    1.2%
    156
    +0.18
    1.1%
    470
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.20
    0.02
    411
    +0.18
    0.02
    470
    +0.14
    0.02
    Negative Logits
    ‘
    -1.38
     discussed
    -1.37
    anson
    -1.36
    âĢŁ
    -1.36
    vereign
    -1.35
    hire
    -1.34
    ="{
    -1.32
    itian
    -1.30
    ael
    -1.29
    ĭ
    -1.29
    POSITIVE LOGITS
    ably
    2.40
    edly
    1.93
     enough
    1.61
     stains
    1.47
     landmarks
    1.46
     gaps
    1.40
     areas
    1.40
     ones
    1.39
     obstacles
    1.38
     portions
    1.37
    Activations Density 0.257%

    No Known Activations