© 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. 2-MLP-SM
    11. 23489
    Prev
    Next
    INDEX
    Explanations

    terms related to pediatric healthcare and its various specializations

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.18
    1.1%
    426
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.01
    448
    +0.12
    0.01
    426
    +0.12
    0.01
    Negative Logits
    ·¸
    -3.08
    º
    -3.02
    Ľ
    -3.00
    ®
    -2.94
    ³
    -2.90
    ¬
    -2.85
    ±
    -2.83
    ¸
    -2.81
    ¶
    -2.78
    ¯
    -2.77
    POSITIVE LOGITS
    ls
    1.65
    lt
    1.51
    iles
    1.50
     habit
    1.41
     cohes
    1.40
    orously
    1.38
     tense
    1.36
     Punjab
    1.36
     common
    1.33
     ${{
    1.32
    Activations Density 0.159%

    No Known Activations