© 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. 25492
    Prev
    Next
    INDEX
    Explanations

    instances of the word "le" in various contexts

    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
    59
    +0.17
    0.9%
    53
    +0.11
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.17
    0.03
    307
    +0.11
    0.02
    203
    +0.11
    0.02
    Negative Logits
    rial
    -1.76
    oddsidemargin
    -1.71
    las
    -1.63
    "))
    -1.50
    UAL
    -1.47
    ünd
    -1.46
    ULL
    -1.43
    ")]
    -1.39
    ARGET
    -1.36
    collapse
    -1.35
    POSITIVE LOGITS
    arner
    1.91
    vy
    1.91
    Ľ
    1.87
    vee
    1.74
    opard
    1.61
    gged
    1.58
    ipzig
    1.56
    ving
    1.51
    Ģ
    1.47
    ittest
    1.45
    Activations Density 0.114%

    No Known Activations