© 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. 1-RES-SM
    11. 25054
    Prev
    Next
    INDEX
    Explanations

    expressions of love and enjoyment related to activities and experiences

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    406
    +0.14
    0.8%
    394
    +0.13
    0.7%
    90
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.14
    0.05
    505
    +0.13
    0.04
    300
    +0.13
    0.05
    Negative Logits
    etermined
    -1.61
     confirmed
    -1.59
     unless
    -1.57
     below
    -1.55
    unct
    -1.52
     until
    -1.52
    aspase
    -1.49
    :$$\
    -1.48
     indicated
    -1.45
    unless
    -1.43
    POSITIVE LOGITS
    ĺ
    2.67
    ĻĤ
    2.50
    ĥ½
    2.48
    Ļª
    2.40
    ĸ
    2.34
    ł
    2.33
    ¾
    2.25
    ĭ
    2.20
    ļ
    2.11
    ŀ
    2.10
    Activations Density 0.720%

    No Known Activations