© 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. 27354
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to environmental regulations and standards

    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
    156
    +0.37
    2.2%
    369
    +0.13
    0.8%
    412
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.37
    0.02
    230
    +0.13
    0.02
    410
    +0.11
    0.05
    Negative Logits
    hood
    -1.96
     bowel
    -1.58
    cluding
    -1.53
     sob
    -1.51
     miscar
    -1.50
     fasting
    -1.49
    itary
    -1.48
     vomiting
    -1.47
    opause
    -1.46
    igmat
    -1.42
    POSITIVE LOGITS
    ILITY
    2.25
    ĨĴ
    2.24
    CC
    2.05
    ERTY
    2.01
    CP
    1.99
    IC
    1.94
    IER
    1.89
    CTL
    1.84
    ERC
    1.81
    SEC
    1.80
    Activations Density 0.396%

    No Known Activations