© 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. 10599
    Prev
    Next
    INDEX
    Explanations

    themes related to regulatory frameworks and compliance mechanisms

    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
    318
    +0.12
    0.7%
    478
    +0.11
    0.6%
    169
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.12
    136
    +0.11
    -0.03
    478
    +0.10
    0.01
    Negative Logits
    ĩ
    -2.28
    ģ
    -2.10
    ĻĤ
    -2.08
    ļ
    -2.05
    Ĵ
    -1.96
    ¬
    -1.92
    »
    -1.88
    ¾
    -1.86
    ¡
    -1.85
    ¨
    -1.82
    POSITIVE LOGITS
    etc
    2.06
     etc
    1.99
    oming
    1.59
    cules
    1.47
     eds
    1.37
     NLR
    1.34
    ubicin
    1.32
     Hann
    1.29
     das
    1.26
    Č
    1.25
    Activations Density 1.498%

    No Known Activations