© 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. 30823
    Prev
    Next
    INDEX
    Explanations

    terms related to amusement park attractions

    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
    67
    +0.13
    0.7%
    380
    +0.12
    0.7%
    16
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.13
    0.38
    310
    +0.12
    0.31
    169
    +0.12
    0.28
    Negative Logits
     matter
    -1.75
    ched
    -1.62
    documentclass
    -1.38
     matters
    -1.36
    ------------------------------------------------------------------------
    -1.33
    nex
    -1.28
    lee
    -1.27
     liberties
    -1.27
    means
    -1.26
    ermost
    -1.26
    POSITIVE LOGITS
    iser
    1.74
    Ļª
    1.73
    tte
    1.69
    ctomy
    1.64
    "}](#
    1.62
    ttes
    1.60
    clerosis
    1.51
    aurus
    1.50
    able
    1.50
    vist
    1.49
    Activations Density 0.982%

    No Known Activations