© 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. 25640
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "we."

    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
    77
    +0.15
    0.8%
    257
    +0.14
    0.8%
    462
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.15
    0.11
    184
    +0.14
    0.10
    138
    +0.14
    0.09
    Negative Logits
    ĺ
    -2.08
    ĻĤ
    -1.99
    ·
    -1.97
    £
    -1.84
    ±
    -1.82
    ĸ
    -1.74
    ¿½
    -1.71
    į
    -1.70
    Ŀ
    -1.66
    Īĺ
    -1.66
    POSITIVE LOGITS
    iginally
    1.54
    nier
    1.52
    :`
    1.50
     authorities
    1.47
    idone
    1.47
    offe
    1.46
    ively
    1.44
     chance
    1.43
     argument
    1.43
    icides
    1.41
    Activations Density 0.174%

    No Known Activations