© 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. 14602
    Prev
    Next
    INDEX
    Explanations

    phrases expressing desire and intention

    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
    320
    +0.18
    1.0%
    186
    +0.13
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.18
    0.18
    411
    +0.13
    0.14
    188
    +0.12
    0.06
    Negative Logits
    Ħ
    -3.15
    İ
    -2.68
    Ĵ
    -2.67
    Ģ
    -2.64
    ¡
    -2.59
    ij
    -2.57
    Ķ
    -2.55
    Ĭ
    -2.47
    ¦
    -2.43
    ¨
    -2.36
    POSITIVE LOGITS
     eat
    2.75
     marry
    2.62
     quit
    2.57
     kill
    2.54
     shoot
    2.40
     lose
    2.33
     retal
    2.33
     sue
    2.31
     ditch
    2.31
     drink
    2.30
    Activations Density 1.604%

    No Known Activations