© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 11767
    Prev
    Next
    INDEX
    Explanations

    phrases related to permission or approval, particularly in legal or formal contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.13
    0.8%
    271
    +0.11
    0.6%
    186
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.01
    334
    +0.11
    0.01
    328
    +0.10
    0.01
    Negative Logits
     proportions
    -1.60
    istics
    -1.57
    ities
    -1.52
    autres
    -1.46
    ientos
    -1.43
    ifiers
    -1.39
    writers
    -1.39
    eter
    -1.38
    astics
    -1.37
    patients
    -1.33
    POSITIVE LOGITS
     hereby
    2.00
     pending
    1.74
     granted
    1.68
     pursuant
    1.50
     _________________________________
    1.49
    [,
    1.45
    ){#
    1.42
     à°
    1.41
    ãĢĢ
    1.41
    č↵
    1.39
    Activations Density 0.024%

    No Known Activations