© 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. 1-RES-SM
    11. 25807
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to decisions, filings, and regulations

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    23
    +0.26
    1.5%
    127
    +0.13
    0.8%
    258
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.26
    0.12
    69
    +0.13
    0.13
    498
    +0.10
    0.08
    Negative Logits
    ®
    -2.63
    Ħ
    -2.34
    ¾
    -2.27
    ½
    -2.26
    ĨĴ
    -2.23
    Ĵ
    -2.21
    ļ
    -2.14
    Ĥ¬
    -2.08
    ¸
    -2.01
    ª
    -1.99
    POSITIVE LOGITS
    ALSE
    1.83
    ETHOD
    1.66
    arers
    1.65
     followed
    1.63
     relieved
    1.55
     supplemented
    1.47
    IRST
    1.44
    ëĭĪëĭ¤
    1.43
    gn
    1.43
    innings
    1.42
    Activations Density 5.157%

    No Known Activations