© 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. Residuals
    9. 1-RES-SM
    11. 28588
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    411
    +0.13
    0.7%
    18
    +0.12
    0.7%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.13
    0.04
    111
    +0.12
    0.05
    202
    +0.12
    0.04
    Negative Logits
    ĥ½
    -3.37
    ī
    -3.22
    IJ
    -3.13
    ģ
    -2.96
    ĺ
    -2.88
    ¤
    -2.85
    ²
    -2.85
    Ĩ
    -2.84
    Ģ
    -2.80
    ¸
    -2.79
    POSITIVE LOGITS
     life
    1.78
     lives
    1.76
    ashes
    1.66
     feet
    1.64
    opy
    1.63
     dollars
    1.54
    emon
    1.53
    eties
    1.52
     souls
    1.51
     heavenly
    1.50
    Activations Density 0.463%

    No Known Activations