© 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. 13690
    Prev
    Next
    INDEX
    Explanations

    information related to political negotiations and agreements, particularly concerning Brexit and associated implications

    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
    235
    +0.12
    0.7%
    64
    +0.11
    0.6%
    29
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.12
    0.12
    235
    +0.11
    0.14
    64
    +0.11
    0.10
    Negative Logits
    ansas
    -2.04
     fibers
    -1.98
     caliber
    -1.94
    Īĺ
    -1.94
     coloring
    -1.90
     <-
    -1.84
    ĥ½
    -1.82
    -1.79
    ↵
    -1.79
    č↵č↵
    -1.79
    POSITIVE LOGITS
     Brexit
    3.51
     MPs
    3.32
     parliament
    3.23
     parliamentary
    3.18
     Parliament
    3.16
     Modi
    3.09
     ministers
    3.08
     Corbyn
    2.95
     Minister
    2.94
     Labour
    2.91
    Activations Density 2.913%

    No Known Activations