© 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. 1-RES-SM
    11. 26279
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "lex" in various contexts related to terminology or products

    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
    350
    +0.15
    0.9%
    380
    +0.15
    0.9%
    369
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.15
    0.02
    155
    +0.15
    0.02
    410
    +0.15
    0.02
    Negative Logits
     else
    -2.45
     other
    -1.60
     particular
    -1.54
    odot
    -1.53
     lesser
    -1.51
    res
    -1.47
     hesitate
    -1.44
     sob
    -1.41
     ELSE
    -1.41
    hin
    -1.41
    POSITIVE LOGITS
    İ
    2.11
    imab
    2.02
    rade
    1.72
    igan
    1.70
    ocur
    1.69
    tern
    1.67
    IONS
    1.60
    mith
    1.60
    ENTIAL
    1.60
    arian
    1.59
    Activations Density 0.126%

    No Known Activations