© 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. 28286
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and obligations

    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
    18
    +0.16
    0.9%
    186
    +0.13
    0.7%
    409
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.17
    156
    +0.13
    0.20
    234
    +0.13
    0.15
    Negative Logits
    ¦
    -2.50
    ij
    -2.49
    ¨
    -2.48
    Ĥ¬
    -2.47
    «
    -2.45
    į
    -2.43
    ĺ
    -2.41
    Į
    -2.37
    ²
    -2.36
    §
    -2.26
    POSITIVE LOGITS
    .
    1.77
     alike
    1.76
     whichever
    1.68
    oley
    1.66
    ”.
    1.62
     any
    1.61
    ”,
    1.57
    )",
    1.57
     depending
    1.57
     thereof
    1.55
    Activations Density 4.121%

    No Known Activations