© 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. 2-RES-SM
    11. 10335
    Prev
    Next
    INDEX
    Explanations

    the word "With" indicating a context or condition in a statement

    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
    358
    +0.15
    0.8%
    478
    +0.13
    0.7%
    282
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.15
    0.05
    358
    +0.13
    0.04
    282
    +0.13
    0.04
    Negative Logits
    cias
    -1.69
     liable
    -1.66
    ary
    -1.57
    arily
    -1.55
    nd
    -1.53
    ther
    -1.48
     LIABLE
    -1.44
    teenth
    -1.41
     {#
    -1.33
    thal
    -1.33
    POSITIVE LOGITS
     respect
    2.44
     regards
    2.39
     regard
    2.38
    drawn
    2.20
     luck
    2.00
    draw
    1.97
    respect
    1.88
    acity
    1.72
    drew
    1.70
    holding
    1.67
    Activations Density 0.170%

    No Known Activations