© 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. 29572
    Prev
    Next
    INDEX
    Explanations

    instances of the word "par"

    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
    376
    +0.12
    0.7%
    181
    +0.11
    0.6%
    362
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.12
    0.01
    312
    +0.11
    0.02
    181
    +0.10
    0.02
    Negative Logits
    Ń
    -4.34
    ĨĴ
    -4.34
    ³
    -4.31
    Īĺ
    -4.15
    ĵ
    -4.12
    »
    -4.07
    ĸ´
    -4.04
    Ĺ
    -3.96
    ĥ½
    -3.96
    ĩ
    -3.95
    POSITIVE LOGITS
    lament
    1.65
    vez
    1.62
    aphr
    1.58
    avel
    1.56
    agraph
    1.55
    aj
    1.55
    holder
    1.54
    rition
    1.53
    agem
    1.52
    iga
    1.51
    Activations Density 0.056%

    No Known Activations