© 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. 10134
    Prev
    Next
    INDEX
    Explanations

    legal terminology and case-related information

    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
    57
    +0.11
    0.6%
    126
    +0.10
    0.6%
    157
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.11
    0.02
    168
    +0.10
    0.02
    57
    +0.10
    0.02
    Negative Logits
    .’
    -1.67
     penny
    -1.66
    ’.
    -1.64
    ?’
    -1.57
    !’
    -1.57
    ocur
    -1.56
     dominating
    -1.53
    ’,
    -1.46
    ,’
    -1.45
     dominate
    -1.43
    POSITIVE LOGITS
    ĥ½
    1.81
     Filed
    1.62
     Levin
    1.59
     Submitted
    1.57
     INTRODUCTION
    1.42
     Hours
    1.38
    FIL
    1.36
     Adv
    1.34
     Appeal
    1.34
    Submitted
    1.33
    Activations Density 0.115%

    No Known Activations