© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30284
    Prev
    Next
    INDEX
    Explanations

    structured legal terms related to court cases

    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
    168
    +0.12
    0.7%
    21
    +0.12
    0.6%
    157
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.12
    0.03
    175
    +0.12
    0.02
    92
    +0.11
    0.03
    Negative Logits
    oche
    -1.67
    ()</
    -1.54
    iting
    -1.50
     wont
    -1.45
     browser
    -1.38
    ()).
    -1.38
    orect
    -1.36
    '):
    -1.36
    itum
    -1.35
    paste
    -1.35
    POSITIVE LOGITS
    ģ
    4.81
    ĥ½
    4.74
    Ĭ
    4.66
    ·
    4.62
    ¹
    4.45
    ³
    4.39
    ·¸
    4.36
    ĻĤ
    4.26
    ŀ
    4.26
    ¸
    4.21
    Activations Density 0.147%

    No Known Activations