© 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. 4-RES-SM
    11. 11511
    Prev
    Next
    INDEX
    Explanations

    phrases associated with empowerment and actionable steps towards personal change

    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
    307
    +0.26
    1.5%
    306
    +0.20
    1.2%
    450
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.26
    0.19
    306
    +0.20
    0.10
    418
    +0.15
    0.06
    Negative Logits
     thereof
    -2.09
    /-
    -1.66
    umably
    -1.61
    amethasone
    -1.60
     ;;
    -1.59
     etc
    -1.54
    arently
    -1.51
    ($_
    -1.51
     kinda
    -1.49
     (_
    -1.47
    POSITIVE LOGITS
     empower
    2.43
     2020
    2.02
     policym
    2.01
     insights
    1.93
     2030
    1.92
     stakeholders
    1.88
     explores
    1.86
     educators
    1.81
     grassroots
    1.78
     inspire
    1.77
    Activations Density 3.549%

    No Known Activations