© 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. 26991
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to set theory and category theory

    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
    280
    +0.15
    0.8%
    405
    +0.13
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.15
    0.02
    151
    +0.13
    0.03
    56
    +0.11
    0.03
    Negative Logits
     chr
    -1.57
     else
    -1.44
    llll
    -1.37
     bras
    -1.34
     average
    -1.33
     audi
    -1.33
     beers
    -1.30
     BB
    -1.30
     bour
    -1.28
     hyperb
    -1.28
    POSITIVE LOGITS
    ondo
    1.72
    ors
    1.57
    Contents
    1.53
    ¦
    1.51
    ipping
    1.49
    or
    1.45
    ij
    1.40
    vant
    1.40
    sov
    1.38
    wood
    1.36
    Activations Density 0.249%

    No Known Activations