© 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. 28864
    Prev
    Next
    INDEX
    Explanations

    references to Western culture and politics

    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
    156
    +0.16
    0.9%
    362
    +0.16
    0.9%
    445
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.03
    445
    +0.16
    0.03
    111
    +0.15
    0.03
    Negative Logits
     negatively
    -1.59
     entirety
    -1.59
     repeat
    -1.57
     certain
    -1.56
     vomiting
    -1.55
     neut
    -1.54
    ocyt
    -1.54
     depolar
    -1.52
     patient
    -1.50
    lessness
    -1.49
    POSITIVE LOGITS
    icum
    2.13
    »¿
    2.06
    ↵
    1.99
    1.99
    ↵
    1.99
    <|outofrange|>
    1.99
            ↵
    1.99
    ↵↵
    1.99
    ↵↵
    1.99
    ↵
    1.99
    Activations Density 0.161%

    No Known Activations