© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 31614
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to power of attorney and decision-making

    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
    263
    +0.31
    1.8%
    186
    +0.16
    0.9%
    24
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.31
    0.22
    407
    +0.16
    0.13
    327
    +0.12
    0.16
    Negative Logits
     respectively
    -1.64
     essays
    -1.50
     freshman
    -1.47
     Wrote
    -1.46
     deported
    -1.41
     graduate
    -1.37
     divorced
    -1.32
    hores
    -1.31
    backs
    -1.31
     degrees
    -1.28
    POSITIVE LOGITS
     fact
    1.41
    aring
    1.41
    č↵		
    1.41
    č↵	
    1.37
     discretion
    1.34
    ://
    1.30
    oscope
    1.29
    ĥ½
    1.29
    const
    1.27
    Tak
    1.27
    Activations Density 5.941%

    No Known Activations