© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 12240
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at 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/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
    271
    +0.16
    0.9%
    23
    +0.15
    0.8%
    412
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.16
    0.04
    321
    +0.15
    0.03
    23
    +0.14
    0.04
    Negative Logits
     himself
    -1.83
    otropic
    -1.73
     herself
    -1.66
    icum
    -1.54
    ich
    -1.51
    asek
    -1.50
     rpm
    -1.48
    gart
    -1.46
    ium
    -1.46
    ieri
    -1.45
    POSITIVE LOGITS
    Ī
    1.61
     However
    1.61
     Secondly
    1.56
    then
    1.52
    ĻĤ
    1.50
    indexOf
    1.48
     Moreover
    1.47
     Furthermore
    1.46
    oxford
    1.46
    ãģĵãģ®
    1.46
    Activations Density 0.104%

    No Known Activations