© 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. 30198
    Prev
    Next
    INDEX
    Explanations

    references to specific cell types used in scientific research

    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
    +0.30
    1.8%
    52
    +0.14
    0.9%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.30
    0.01
    71
    +0.14
    0.00
    156
    +0.12
    0.00
    Negative Logits
    ĥ½
    -1.72
    verted
    -1.67
    woke
    -1.54
    į
    -1.51
     clerk
    -1.45
    ¯
    -1.42
     grin
    -1.42
     pronounced
    -1.41
    ĥ
    -1.41
     że
    -1.40
    POSITIVE LOGITS
    istor
    2.12
    oors
    1.72
    ocide
    1.70
    istors
    1.62
    ential
    1.55
    ome
    1.51
    ycin
    1.49
    SEC
    1.44
    ulous
    1.40
    kill
    1.38
    Activations Density 0.009%

    No Known Activations