© 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. 26416
    Prev
    Next
    INDEX
    Explanations

    the word "For" at the beginning of sentences

    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
    448
    +0.13
    0.7%
    323
    +0.11
    0.6%
    14
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.13
    0.04
    381
    +0.11
    0.04
    60
    +0.10
    0.04
    Negative Logits
    cludes
    -1.67
    erate
    -1.55
    apshot
    -1.51
    sets
    -1.50
     summary
    -1.45
    clinical
    -1.39
    oku
    -1.39
    pt
    -1.39
    lined
    -1.37
    cheon
    -1.37
    POSITIVE LOGITS
    ––––––––
    1.55
     fires
    1.54
    imir
    1.52
    ®
    1.51
    lems
    1.48
     penet
    1.46
    vue
    1.46
    ©
    1.45
    (){
    1.45
    oxide
    1.41
    Activations Density 0.017%

    No Known Activations