© 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. 28145
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this."

    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
    134
    +0.16
    0.9%
    464
    +0.13
    0.8%
    67
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.16
    0.15
    26
    +0.13
    0.14
    199
    +0.13
    0.14
    Negative Logits
    rass
    -1.59
    awk
    -1.57
    hou
    -1.47
    astro
    -1.43
    raud
    -1.39
    acci
    -1.39
    inj
    -1.36
    bow
    -1.34
     wonder
    -1.34
    ymph
    -1.33
    POSITIVE LOGITS
    µ
    1.66
    acting
    1.57
    Ŀ
    1.57
    Ń
    1.54
    ¬
    1.42
    ´
    1.42
    gaard
    1.39
    ļ
    1.38
    Ģ
    1.38
    Ĩ
    1.37
    Activations Density 0.274%

    No Known Activations