© 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 EvalsExportsAPI 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. 28847
    Prev
    Next
    INDEX
    Explanations

    mentions of "studio" and related terms

    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
    156
    +0.21
    1.3%
    16
    +0.13
    0.7%
    476
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.21
    0.01
    476
    +0.13
    0.01
    329
    +0.11
    0.01
    Negative Logits
    leep
    -1.79
    woke
    -1.56
     Amazon
    -1.54
     Es
    -1.51
    sole
    -1.50
     favorable
    -1.45
     Sen
    -1.40
     Springer
    -1.38
    apine
    -1.36
     pleasure
    -1.36
    POSITIVE LOGITS
    pieces
    1.90
    ctions
    1.74
    imeter
    1.63
    holm
    1.57
    imetry
    1.54
    hoc
    1.53
    eral
    1.52
    amental
    1.50
    esy
    1.49
    notes
    1.47
    Activations Density 0.016%

    No Known Activations