© 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. 4-RES-SM
    11. 9003
    Prev
    Next
    INDEX
    Explanations

    questions related to existential themes and human nature

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    298
    +0.19
    1.1%
    246
    +0.16
    0.9%
    363
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.19
    0.07
    390
    +0.16
    0.09
    476
    +0.15
    0.08
    Negative Logits
    ĥ½
    -3.85
    ¾
    -3.71
    ½
    -3.58
    ħ
    -3.51
    Ħ
    -3.48
    ij
    -3.48
    ŀ
    -3.43
    Ĥ
    -3.42
    ©
    -3.41
    į
    -3.35
    POSITIVE LOGITS
     why
    3.07
    why
    2.90
     how
    2.86
    how
    2.86
     Does
    2.36
     Why
    2.36
     what
    2.31
     How
    2.29
    what
    2.13
    sure
    2.08
    Activations Density 0.834%

    No Known Activations