© 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. 30430
    Prev
    Next
    INDEX
    Explanations

    references to dates and events in legal 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/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
    410
    +0.18
    1.0%
    289
    +0.14
    0.8%
    373
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.18
    0.02
    373
    +0.14
    0.02
    289
    +0.11
    0.01
    Negative Logits
    etc
    -2.10
     respectively
    -1.79
    ?’
    -1.58
    iph
    -1.54
    raise
    -1.52
    posable
    -1.50
    uran
    -1.49
    ipes
    -1.48
    âĢ¦”
    -1.47
    autre
    -1.46
    POSITIVE LOGITS
     Appeal
    1.94
    ¾
    1.69
     attorneys
    1.65
    Appeal
    1.57
     ----,
    1.47
     Appellate
    1.46
     Li
    1.45
    NEY
    1.43
     Stevens
    1.42
     motions
    1.39
    Activations Density 0.041%

    No Known Activations