© 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. 2-RES-SM
    11. 31873
    Prev
    Next
    INDEX
    Explanations

    elements of legal proceedings and 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/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
    186
    +0.16
    0.9%
    470
    +0.11
    0.6%
    509
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.16
    0.12
    470
    +0.11
    0.17
    96
    +0.10
    0.02
    Negative Logits
     labelling
    -1.63
     glance
    -1.57
     overlook
    -1.57
     scientists
    -1.54
     labeling
    -1.53
     record
    -1.51
     below
    -1.50
     simplest
    -1.49
     absorbance
    -1.46
     swelling
    -1.45
    POSITIVE LOGITS
    Ļª
    3.62
    ¶
    2.99
    ¦
    2.86
    Ĥ¬
    2.86
    »¿
    2.83
    IJ
    2.75
    ¿½
    2.69
    ľĵ
    2.63
    ī
    2.63
    ģ
    2.61
    Activations Density 5.964%

    No Known Activations