© 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. 4-RES-SM
    11. 10308
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences or clauses

    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
    156
    +0.13
    0.8%
    136
    +0.11
    0.6%
    502
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    425
    +0.13
    0.05
    130
    +0.11
    0.05
    502
    +0.11
    0.04
    Negative Logits
    Ļ
    -5.14
    Ļª
    -4.93
    ļ
    -4.88
    »
    -4.82
    °
    -4.81
    -4.75
    -4.75
    ↵↵↵
    -4.75
    č↵č↵
    -4.75
              ↵
    -4.75
    POSITIVE LOGITS
     Ltd
    1.67
     {#
    1.65
     —
    1.60
     –
    1.59
     ):
    1.58
     Honorable
    1.58
     edition
    1.56
    ãģķãĤĵ
    1.51
     ,"
    1.50
     ,
    1.48
    Activations Density 0.234%

    No Known Activations