© 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. 25510
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols, particularly focusing on quotes and apostrophes in the text

    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
    505
    +0.17
    1.0%
    220
    +0.13
    0.7%
    430
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.17
    0.01
    505
    +0.13
    0.01
    456
    +0.12
    0.01
    Negative Logits
     normalized
    -1.74
     ?"
    -1.63
     operated
    -1.60
    onic
    -1.50
     handling
    -1.50
     parameters
    -1.48
     normalization
    -1.47
    ometer
    -1.47
     scale
    -1.46
     discrim
    -1.46
    POSITIVE LOGITS
    ®
    4.19
    Ģ
    3.68
    ħ
    3.64
    ¹
    3.64
    ŀ
    3.63
    ĭ
    3.51
    ¼
    3.51
    Į
    3.48
    ĥ
    3.47
    Ĭ
    3.39
    Activations Density 0.097%

    No Known Activations