© 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. 28254
    Prev
    Next
    INDEX
    Explanations

    instances of the word "juicy."

    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
    180
    +0.12
    0.7%
    300
    +0.12
    0.7%
    149
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.12
    0.01
    300
    +0.12
    0.01
    149
    +0.11
    0.01
    Negative Logits
     ')
    -1.71
    usions
    -1.54
     '</
    -1.52
     respectively
    -1.51
     latter
    -1.50
    ieurs
    -1.43
     ")
    -1.43
     daytime
    -1.39
     ");
    -1.38
    '));
    -1.38
    POSITIVE LOGITS
    ¢
    2.38
    ģ
    2.35
    Ĵ
    2.14
    Ł
    1.97
    Ķ
    1.92
    ±
    1.91
    ŀ
    1.84
    Ŀ
    1.81
    ¸
    1.80
    ķ
    1.75
    Activations Density 0.011%

    No Known Activations