© 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. 26480
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to"

    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
    209
    +0.12
    0.7%
    255
    +0.12
    0.6%
    28
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.05
    109
    +0.12
    0.04
    434
    +0.12
    0.04
    Negative Logits
    .[@
    -1.51
    ´
    -1.41
    rios
    -1.41
    $.\
    -1.40
    .[^
    -1.39
    ettes
    -1.36
    ĻĤ
    -1.35
    ères
    -1.34
     {#
    -1.34
    »¿
    -1.33
    POSITIVE LOGITS
    wn
    1.62
     desperation
    1.49
    ed
    1.45
     deal
    1.44
    own
    1.37
    istically
    1.36
    opan
    1.34
    atform
    1.33
    pped
    1.33
    tested
    1.31
    Activations Density 0.030%

    No Known Activations