© 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. 26407
    Prev
    Next
    INDEX
    Explanations

    terms related to exceptions in coding frameworks and system operations

    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
    446
    +0.14
    0.8%
    260
    +0.12
    0.7%
    391
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.14
    0.02
    260
    +0.12
    0.02
    285
    +0.11
    0.02
    Negative Logits
    ){#
    -1.72
    ency
    -1.59
    rceil
    -1.59
    yel
    -1.58
    uties
    -1.55
    )}^{
    -1.53
     \,\
    -1.52
     preponderance
    -1.51
     '</
    -1.47
     sync
    -1.47
    POSITIVE LOGITS
    ®
    2.20
    ª
    2.04
    CAR
    1.99
    creen
    1.94
    Ĥ¬
    1.91
    PER
    1.89
    µ
    1.88
    Ļª
    1.83
    ´
    1.81
    ¿
    1.80
    Activations Density 0.068%

    No Known Activations