© 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. 29554
    Prev
    Next
    INDEX
    Explanations

    occurrences 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
    28
    +0.12
    0.6%
    164
    +0.11
    0.6%
    114
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.46
    98
    +0.11
    0.22
    23
    +0.11
    0.37
    Negative Logits
    ¿
    -2.92
    ¨
    -2.83
    »¿
    -2.78
    Ĩ
    -2.67
    ¹
    -2.66
    ¤
    -2.63
    ½
    -2.56
    ĩ
    -2.53
    £
    -2.51
    ¢
    -2.45
    POSITIVE LOGITS
    antry
    1.71
    pez
    1.59
    rait
    1.48
    gebra
    1.46
    ysis
    1.44
    culus
    1.40
    inent
    1.40
     prominently
    1.40
    able
    1.39
     sculpt
    1.37
    Activations Density 5.990%

    No Known Activations