© 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. 27683
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "another"

    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
    239
    +0.13
    0.8%
    362
    +0.13
    0.7%
    359
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.13
    0.05
    359
    +0.13
    0.05
    199
    +0.12
    0.04
    Negative Logits
    ards
    -1.60
    arde
    -1.57
    ende
    -1.51
    ors
    -1.51
    esta
    -1.49
    roc
    -1.41
    apine
    -1.41
     Rapids
    -1.36
    prom
    -1.33
     balloons
    -1.32
    POSITIVE LOGITS
     than
    1.69
    than
    1.61
    world
    1.58
    Than
    1.58
     liking
    1.57
    leans
    1.57
     possible
    1.55
    gree
    1.54
     hundred
    1.51
    uras
    1.49
    Activations Density 0.516%

    No Known Activations