© 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. 2-RES-SM
    11. 10816
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and social protection issues

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    186
    +0.27
    1.5%
    56
    +0.14
    0.8%
    372
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.27
    0.12
    149
    +0.14
    0.10
    56
    +0.11
    -0.03
    Negative Logits
     annealing
    -1.58
     centrifugation
    -1.46
     anne
    -1.40
     dated
    -1.40
     recommendation
    -1.35
     RSV
    -1.33
     applications
    -1.31
     angiography
    -1.31
     Graph
    -1.30
    uction
    -1.30
    POSITIVE LOGITS
     vulnerable
    1.86
     stature
    1.74
     innocent
    1.74
     humanity
    1.62
     peoples
    1.59
    uters
    1.57
     aggress
    1.56
    ľ
    1.54
    ĺ
    1.52
     victims
    1.50
    Activations Density 2.950%

    No Known Activations