© 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. 0-MLP-SM
    11. 29280
    Prev
    Next
    INDEX
    Explanations

    descriptors indicative of glamour or extravagance

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    362
    +0.13
    0.7%
    260
    +0.11
    0.6%
    219
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.13
    0.01
    260
    +0.11
    0.01
    19
    +0.11
    0.01
    Negative Logits
     say
    -1.69
     stratified
    -1.61
     dich
    -1.61
     disagree
    -1.57
     discriminated
    -1.56
     equal
    -1.54
     warn
    -1.53
     brightest
    -1.53
     treated
    -1.53
     pristine
    -1.53
    POSITIVE LOGITS
    gio
    2.54
    forge
    2.35
    framework
    2.12
    ĻĤ
    2.12
    ¿½
    2.04
    ware
    1.99
    "}](#
    1.92
    emente
    1.85
    ¹
    1.85
    ŀ
    1.83
    Activations Density 0.007%

    No Known Activations