© 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. 28453
    Prev
    Next
    INDEX
    Explanations

    instances of the word "orchestrate."

    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
    410
    +0.13
    0.7%
    5
    +0.13
    0.7%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.13
    0.01
    111
    +0.13
    0.01
    132
    +0.12
    0.01
    Negative Logits
     potential
    -1.49
     attraction
    -1.47
     Carol
    -1.41
     addition
    -1.40
     recovery
    -1.36
    MR
    -1.36
    \%
    -1.35
     introduction
    -1.33
     guidance
    -1.31
     margin
    -1.28
    POSITIVE LOGITS
    Ĵ
    3.61
    ©
    3.34
    ĻĤ
    3.31
    º
    3.23
    ·
    3.16
    ²
    3.13
    ¥
    3.07
    ¸
    3.06
    ½
    3.05
    İ
    3.03
    Activations Density 0.012%

    No Known Activations