© 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. 14731
    Prev
    Next
    INDEX
    Explanations

    mentions of falsehoods, misinformation, and claims about truth and reliability

    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
    306
    +0.22
    1.2%
    156
    +0.13
    0.7%
    268
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.22
    0.04
    198
    +0.13
    0.07
    326
    +0.11
    0.05
    Negative Logits
    »¿
    -1.94
    ĵ
    -1.91
    ĨĴ
    -1.91
    Ķ
    -1.87
    ĺ
    -1.83
    IJ
    -1.78
    ·¸
    -1.73
    ¥
    -1.69
    ķ
    -1.68
    ĥ½
    -1.59
    POSITIVE LOGITS
    fulness
    2.23
     tales
    2.09
     fiction
    2.02
    truth
    2.00
     tale
    1.98
     truth
    1.93
    itious
    1.89
     truths
    1.88
     facts
    1.88
     narratives
    1.86
    Activations Density 1.174%

    No Known Activations