© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27314
    Prev
    Next
    INDEX
    Explanations

    verbs indicating statements or claims made by individuals

    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
    115
    +0.15
    0.9%
    478
    +0.14
    0.8%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.15
    0.05
    323
    +0.14
    0.04
    120
    +0.13
    0.03
    Negative Logits
    ¾
    -2.93
    ĥ½
    -2.86
    ¡
    -2.82
    į
    -2.71
    »¿
    -2.65
    ·¸
    -2.61
    ¬
    -2.61
    IJ
    -2.58
    ĨĴ
    -2.55
    ¹
    -2.55
    POSITIVE LOGITS
     concern
    2.11
     lack
    1.79
    ffect
    1.64
     autopsy
    1.57
     missing
    1.56
     diagnostic
    1.55
     abnormal
    1.53
     inadequate
    1.52
    olate
    1.51
     fetal
    1.50
    Activations Density 0.202%

    No Known Activations