© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-MLP-SM
    11. 25678
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements related to size or dimensions

    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
    59
    +0.16
    0.9%
    23
    +0.14
    0.7%
    425
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.16
    0.03
    59
    +0.14
    -0.00
    50
    +0.12
    0.01
    Negative Logits
    naire
    -1.69
    kok
    -1.51
     NSW
    -1.45
    DOM
    -1.38
    ů
    -1.36
     vars
    -1.36
    reon
    -1.35
     CIRCUIT
    -1.32
    ului
    -1.32
    URAL
    -1.32
    POSITIVE LOGITS
    eration
    1.74
    º
    1.59
    you
    1.51
    ¹
    1.40
    izontal
    1.37
     toe
    1.34
     bored
    1.30
    etter
    1.29
     learners
    1.28
    ·¸
    1.25
    Activations Density 0.613%

    No Known Activations