© 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. 14160
    Prev
    Next
    INDEX
    Explanations

    references to specific molecules and chemical elements

    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
    466
    +0.18
    1.1%
    25
    +0.18
    1.0%
    307
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.18
    0.10
    100
    +0.18
    0.09
    466
    +0.15
    0.10
    Negative Logits
    ĻĤ
    -3.76
    ģ
    -3.26
    ľĵ
    -2.88
    »¿
    -2.84
    ĥ
    -2.80
    ĨĴ
    -2.77
    ĵ
    -2.73
    ħ
    -2.73
    ¾
    -2.72
    Į
    -2.70
    POSITIVE LOGITS
    which
    2.52
     which
    2.33
     namely
    2.25
    whose
    2.04
    although
    1.98
     consisting
    1.91
    namely
    1.89
    named
    1.86
     termed
    1.84
     whereby
    1.79
    Activations Density 0.904%

    No Known Activations