© 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. 2-RES-SM
    11. 30922
    Prev
    Next
    INDEX
    Explanations

    the word "just."

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    110
    +0.17
    1.0%
    354
    +0.13
    0.8%
    241
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.17
    0.06
    241
    +0.13
    0.07
    2
    +0.13
    0.06
    Negative Logits
    ĨĴ
    -2.19
    Ģ
    -2.05
    ļ
    -1.95
    »¿
    -1.84
    soever
    -1.83
    Ļª
    -1.82
    ħ
    -1.78
    ĭ
    -1.77
    ĵ
    -1.74
    Ĥ¬
    -1.73
    POSITIVE LOGITS
    ifi
    2.39
    ifiable
    2.29
     kidding
    2.15
    ified
    2.10
    ifications
    1.96
    ifying
    1.95
     plain
    1.86
     shy
    1.76
    IFY
    1.72
    ky
    1.71
    Activations Density 0.166%

    No Known Activations