© 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. 30944
    Prev
    Next
    INDEX
    Explanations

    instances of the word "able"

    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
    348
    +0.14
    0.8%
    406
    +0.13
    0.7%
    181
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.14
    0.02
    406
    +0.13
    0.02
    181
    +0.12
    0.02
    Negative Logits
    meric
    -1.50
     certain
    -1.43
     forecast
    -1.43
     fair
    -1.41
    "?"
    -1.38
    >`
    -1.38
     therefore
    -1.37
    ${
    -1.35
    "`
    -1.35
    pher
    -1.34
    POSITIVE LOGITS
    ĻĤ
    2.82
    º
    2.05
    enstein
    1.85
    ¹
    1.71
    ename
    1.70
    anguage
    1.70
    enos
    1.62
    enas
    1.59
    eno
    1.59
    fest
    1.57
    Activations Density 0.011%

    No Known Activations