© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29381
    Prev
    Next
    INDEX
    Explanations

    instances of the word "begins."

    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
    170
    +0.14
    0.8%
    40
    +0.14
    0.8%
    385
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.14
    0.02
    423
    +0.14
    0.02
    59
    +0.12
    0.02
    Negative Logits
    bones
    -1.88
     thereof
    -1.71
    lasses
    -1.55
    pie
    -1.53
    ktop
    -1.49
     adipocytes
    -1.45
    models
    -1.45
    hire
    -1.45
    ods
    -1.43
     sino
    -1.42
    POSITIVE LOGITS
    Follow
    1.64
     exception
    1.35
     tolerate
    1.34
     habit
    1.34
    ĥ½
    1.33
     Protection
    1.31
    handle
    1.31
     Stop
    1.31
    iser
    1.30
     abst
    1.30
    Activations Density 0.036%

    No Known Activations