© 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. 25634
    Prev
    Next
    INDEX
    Explanations

    verbs indicating conclusions or suggestions

    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
    283
    +0.14
    0.8%
    98
    +0.12
    0.7%
    194
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.04
    283
    +0.12
    0.04
    194
    +0.12
    0.03
    Negative Logits
     ')
    -1.43
     pur
    -1.42
    like
    -1.40
     smell
    -1.39
     overflow
    -1.37
     lia
    -1.36
     normalize
    -1.35
     divert
    -1.34
     sh
    -1.32
     construed
    -1.31
    POSITIVE LOGITS
    bies
    1.77
    itude
    1.76
    usiness
    1.76
    AIL
    1.66
    bie
    1.65
    izione
    1.63
    enez
    1.61
    ings
    1.60
    iti
    1.57
    izumab
    1.56
    Activations Density 0.120%

    No Known Activations