© 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. 27302
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and documentation

    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
    104
    +0.17
    1.0%
    231
    +0.12
    0.6%
    326
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.17
    0.03
    452
    +0.12
    0.03
    104
    +0.11
    0.03
    Negative Logits
    ettle
    -1.53
     yourself
    -1.52
     basics
    -1.48
    imes
    -1.45
    àµį
    -1.44
     makeup
    -1.42
     theory
    -1.41
     daddy
    -1.41
    )!
    -1.39
     your
    -1.38
    POSITIVE LOGITS
    nor
    1.88
    pril
    1.83
     hereby
    1.44
    umns
    1.43
    000
    1.42
    0018
    1.38
    arro
    1.38
     sino
    1.38
    &=&\
    1.37
    PLL
    1.37
    Activations Density 0.126%

    No Known Activations