© 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. 25441
    Prev
    Next
    INDEX
    Explanations

    text related to the topic of genetic research and diseases

    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
    111
    +0.12
    0.7%
    364
    +0.11
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.01
    500
    +0.11
    0.01
    422
    +0.11
    0.00
    Negative Logits
    ables
    -1.90
    nez
    -1.79
    able
    -1.62
     respectively
    -1.56
    ably
    -1.52
    unreadable
    -1.50
    abil
    -1.48
    Ķ
    -1.45
    oles
    -1.43
    paces
    -1.43
    POSITIVE LOGITS
    dess
    1.54
    arate
    1.52
    stream
    1.48
    oplasmic
    1.45
    state
    1.44
    rÃŃ
    1.41
     Ages
    1.38
    arty
    1.36
    step
    1.35
    apest
    1.32
    Activations Density 0.009%

    No Known Activations