© 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 EvalsExportsinterp-engineNEWAPI 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. 30841
    Prev
    Next
    INDEX
    Explanations

    references to the term "any" in various contexts, particularly in legal or conditional statements

    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
    87
    +0.14
    0.8%
    478
    +0.13
    0.7%
    436
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    428
    +0.14
    0.08
    87
    +0.13
    0.08
    436
    +0.11
    0.07
    Negative Logits
     atmosp
    -1.71
    roc
    -1.58
    ificant
    -1.45
    dog
    -1.42
     oper
    -1.41
    houses
    -1.37
    nement
    -1.37
    orphic
    -1.37
    representation
    -1.36
     {}
    -1.35
    POSITIVE LOGITS
    thin
    1.79
     WARRANTY
    1.75
     longer
    1.56
    how
    1.56
     harder
    1.52
    onin
    1.48
     better
    1.44
    amycin
    1.43
    iasis
    1.42
    quilibrium
    1.41
    Activations Density 0.079%

    No Known Activations