© 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. 2-MLP-SM
    11. 24946
    Prev
    Next
    INDEX
    Explanations

    numeric values related to prices or monetary amounts

    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
    1.0%
    103
    +0.11
    0.6%
    174
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.18
    0.05
    23
    +0.11
    0.03
    360
    +0.10
    0.01
    Negative Logits
     matches
    -1.58
     offers
    -1.45
    pieces
    -1.43
     touches
    -1.40
    piece
    -1.39
     binder
    -1.38
    _->
    -1.37
     weighs
    -1.35
     finishes
    -1.34
    izes
    -1.34
    POSITIVE LOGITS
    ĻĤ
    2.34
    į
    2.34
    ĩ
    1.98
    ĸ´
    1.94
    Īĺ
    1.87
    ĭ
    1.79
    Ł
    1.79
    Ĥ¬
    1.78
    ĸ
    1.70
    ´
    1.67
    Activations Density 0.375%

    No Known Activations