© 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. 4-RES-SM
    11. 10565
    Prev
    Next
    INDEX
    Explanations

    numerical references, particularly related to legal or judicial 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.18
    1.0%
    255
    +0.14
    0.8%
    299
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.18
    0.03
    78
    +0.14
    0.00
    350
    +0.12
    0.03
    Negative Logits
     transmembrane
    -1.45
    uniform
    -1.44
    hers
    -1.44
    network
    -1.41
    tons
    -1.40
    omerase
    -1.40
    guard
    -1.39
    staff
    -1.38
    coding
    -1.37
    pins
    -1.33
    POSITIVE LOGITS
    į
    3.25
    ĭ
    3.08
    °
    3.05
    İ
    2.71
    ķ
    2.68
    ¸
    2.66
    ĥ½
    2.60
    Ŀ
    2.56
    ´
    2.55
    Į
    2.53
    Activations Density 0.107%

    No Known Activations