© 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. 30716
    Prev
    Next
    INDEX
    Explanations

    the word "which" in various contexts

    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
    0.7%
    397
    +0.12
    0.7%
    107
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.13
    0.03
    65
    +0.12
    0.02
    12
    +0.12
    0.02
    Negative Logits
    msgstr
    -1.51
    UC
    -1.45
    @{
    -1.45
     wishing
    -1.37
     FIG
    -1.37
     Computing
    -1.36
    such
    -1.34
     Cho
    -1.33
    .")
    -1.33
     ##
    -1.32
    POSITIVE LOGITS
    »¿
    1.89
    Į
    1.85
    eries
    1.83
    aliana
    1.68
    į
    1.68
    Ļ
    1.65
    chers
    1.63
    iley
    1.62
    olia
    1.59
    ibile
    1.58
    Activations Density 0.025%

    No Known Activations