© 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 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. 10533
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or entities related to law enforcement and public services

    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
    98
    +0.18
    1.1%
    155
    +0.13
    0.8%
    181
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.18
    0.11
    181
    +0.13
    0.09
    66
    +0.13
    0.10
    Negative Logits
    =${
    -1.91
    =/
    -1.69
     decir
    -1.64
    ="/
    -1.62
    =$(
    -1.58
     formalin
    -1.57
    ="${
    -1.53
    ="'
    -1.50
    edly
    -1.50
    ="$
    -1.45
    POSITIVE LOGITS
     itself
    1.89
    ème
    1.69
     Mountains
    1.55
     Sisters
    1.54
     Collaboration
    1.54
    same
    1.53
     Revolution
    1.52
    ancer
    1.52
     regime
    1.50
    oscope
    1.48
    Activations Density 1.352%

    No Known Activations