© 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. 28639
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to income and wealth

    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
    +0.17
    1.0%
    166
    +0.14
    0.8%
    125
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.17
    0.01
    219
    +0.14
    0.03
    166
    +0.14
    0.02
    Negative Logits
    IJ
    -2.10
    º
    -2.10
    Ĥ¬
    -2.05
    ĨĴ
    -1.99
    Īĺ
    -1.84
    ³
    -1.83
    ushed
    -1.82
    »
    -1.79
    woke
    -1.79
    ¿½
    -1.78
    POSITIVE LOGITS
    chart
    1.71
     tax
    1.69
     distribution
    1.66
    holder
    1.65
     taxes
    1.65
    worth
    1.63
     deposit
    1.55
    ier
    1.53
    -$
    1.51
     income
    1.49
    Activations Density 0.153%

    No Known Activations