© 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. 30416
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to experimental controls in scientific studies

    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
    156
    +0.14
    0.8%
    45
    +0.11
    0.6%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.14
    0.02
    461
    +0.11
    0.02
    277
    +0.11
    0.01
    Negative Logits
    >&
    -1.60
    lio
    -1.49
     IEEE
    -1.48
     >>>
    -1.40
    >>>
    -1.39
     atomic
    -1.38
     remotely
    -1.34
     recharge
    -1.33
    EOF
    -1.31
     @
    -1.31
    POSITIVE LOGITS
    groups
    2.05
     groups
    1.91
    aho
    1.79
    ĻĤ
    1.70
     subgroups
    1.69
     subjects
    1.66
    igon
    1.58
    girl
    1.57
    group
    1.56
    expect
    1.54
    Activations Density 0.124%

    No Known Activations