© 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. 27146
    Prev
    Next
    INDEX
    Explanations

    words associated with research and examination processes

    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
    489
    +0.14
    0.7%
    282
    +0.12
    0.7%
    158
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.14
    0.03
    282
    +0.12
    0.02
    158
    +0.11
    0.02
    Negative Logits
    Ĵ
    -2.99
    Ľ
    -2.96
    ŀ
    -2.80
    ĺ
    -2.73
    ħ
    -2.72
    į
    -2.70
    §
    -2.69
    Ķ
    -2.67
    Īĺ
    -2.61
    Ļ
    -2.57
    POSITIVE LOGITS
     feasibility
    1.83
     whether
    1.81
    getInstance
    1.44
     matters
    1.42
    rese
    1.40
     why
    1.39
     investigating
    1.37
    blic
    1.37
    validate
    1.34
    óg
    1.33
    Activations Density 0.106%

    No Known Activations