© 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. 29698
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that"

    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
    452
    +0.13
    0.7%
    26
    +0.13
    0.7%
    491
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.13
    0.18
    86
    +0.13
    0.18
    120
    +0.13
    0.18
    Negative Logits
    =”
    -1.78
    izza
    -1.75
    iano
    -1.69
    blogger
    -1.67
    icans
    -1.66
     Mario
    -1.56
     Ric
    -1.51
    ="
    -1.49
    osa
    -1.46
    ios
    -1.46
    POSITIVE LOGITS
    µ
    1.94
    IJ
    1.86
    ·
    1.69
    ¸
    1.66
    ·¸
    1.63
    į
    1.61
    ¯
    1.55
    ĥ½
    1.54
    Ķ
    1.51
    ®
    1.50
    Activations Density 0.607%

    No Known Activations