© 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. 28924
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "The"

    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
    23
    +0.25
    1.4%
    203
    +0.15
    0.9%
    351
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.25
    0.11
    129
    +0.15
    0.06
    322
    +0.13
    0.08
    Negative Logits
    ¼
    -2.47
    Ń
    -2.11
    «
    -1.96
    aille
    -1.94
    ¾
    -1.72
    ,...
    -1.69
    ½
    -1.61
    wagen
    -1.60
    !,
    -1.59
    ...)
    -1.59
    POSITIVE LOGITS
     namely
    1.79
     firstly
    1.57
     including
    1.50
     selected
    1.49
    namely
    1.47
    wards
    1.46
    eren
    1.44
    along
    1.44
    AMS
    1.43
    corresponding
    1.42
    Activations Density 0.163%

    No Known Activations