© 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 EvalsExportsinterp-engineNEWAPI 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. 29213
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in legal language or terminology

    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
    271
    +0.17
    1.0%
    478
    +0.13
    0.8%
    22
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.17
    0.05
    111
    +0.13
    0.13
    17
    +0.10
    0.06
    Negative Logits
    ibo
    -1.49
    ço
    -1.48
    ji
    -1.48
    icro
    -1.45
    icillin
    -1.44
    genes
    -1.43
     counterparts
    -1.43
    rences
    -1.43
    isation
    -1.42
     sectors
    -1.40
    POSITIVE LOGITS
    ŀ
    2.59
    »¿
    2.39
    Ļª
    2.30
    Ī
    2.19
    ½
    2.16
    ©
    2.16
    ¹
    2.15
    °
    2.09
    ľ
    2.01
    Īĺ
    1.97
    Activations Density 0.609%

    No Known Activations