© 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. 25487
    Prev
    Next
    INDEX
    Explanations

    references to oligarchs or oligarchic systems

    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
    71
    +0.16
    0.9%
    289
    +0.13
    0.7%
    111
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.06
    271
    +0.13
    0.02
    156
    +0.10
    0.03
    Negative Logits
     brightest
    -1.88
    lessly
    -1.66
     pupils
    -1.49
    hire
    -1.43
     clear
    -1.42
     cheerful
    -1.41
     NOTICE
    -1.41
     Lucy
    -1.40
    ruit
    -1.36
    unners
    -1.35
    POSITIVE LOGITS
    İ
    2.08
    Ĵ
    2.02
    ģ
    1.62
    enium
    1.61
    ī
    1.61
    archy
    1.54
    Ľ
    1.51
    obe
    1.50
    weg
    1.50
    arch
    1.49
    Activations Density 0.130%

    No Known Activations