© 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 EvalsExportsinterp-engineNEWAPI 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. 30362
    Prev
    Next
    INDEX
    Explanations

    references to the state of Iowa

    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
    369
    +0.13
    0.8%
    182
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.13
    0.02
    160
    +0.12
    0.02
    182
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.05
    ¿
    -1.78
    Ħ
    -1.65
    ´
    -1.64
    usterity
    -1.58
     everything
    -1.56
     bowel
    -1.55
    '));
    -1.51
     complete
    -1.51
    ages
    -1.50
    POSITIVE LOGITS
    leen
    2.05
    ian
    1.78
    fonts
    1.62
     vs
    1.61
    iop
    1.58
    eral
    1.58
    ibernate
    1.57
     Comics
    1.57
    bolt
    1.53
    naire
    1.53
    Activations Density 0.010%

    No Known Activations