© 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. 28633
    Prev
    Next
    INDEX
    Explanations

    references to small or diminutive things

    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
    375
    +0.14
    0.8%
    305
    +0.12
    0.7%
    472
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.14
    0.06
    305
    +0.12
    0.05
    472
    +0.12
    0.05
    Negative Logits
    roc
    -1.98
    ying
    -1.55
    odor
    -1.54
    amp
    -1.49
    ault
    -1.46
    hyd
    -1.45
     countless
    -1.44
    forcement
    -1.44
    antic
    -1.43
    č↵
    -1.39
    POSITIVE LOGITS
    ¿½
    1.82
    ł
    1.74
     revisions
    1.50
     avail
    1.50
     finale
    1.49
     feat
    1.44
    NON
    1.38
     resem
    1.37
    {}{
    1.37
    =\"
    1.35
    Activations Density 0.959%

    No Known Activations