© 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. 2-RES-SM
    11. 27683
    Prev
    Next
    INDEX
    Explanations

    references to security and protective services, particularly in relation to guards and military

    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
    115
    +0.13
    0.7%
    426
    +0.12
    0.7%
    191
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.13
    0.04
    253
    +0.12
    0.03
    181
    +0.11
    0.03
    Negative Logits
    ching
    -1.66
    quire
    -1.66
     little
    -1.50
     rich
    -1.47
     happy
    -1.41
     pleasant
    -1.40
     quick
    -1.39
     lucky
    -1.38
     sender
    -1.36
     well
    -1.36
    POSITIVE LOGITS
    igan
    2.28
    ian
    2.27
    edly
    2.13
    iale
    2.10
    aic
    2.08
    ians
    2.02
    esy
    2.01
    iani
    1.96
    iera
    1.94
    ieri
    1.92
    Activations Density 0.392%

    No Known Activations