© 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. 11850
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or symbols, particularly commas and quotation marks

    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
    397
    +0.19
    1.1%
    466
    +0.15
    0.8%
    131
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.19
    0.07
    315
    +0.15
    0.08
    131
    +0.13
    0.08
    Negative Logits
    ively
    -1.71
    ishly
    -1.39
    rically
    -1.37
    ViewController
    -1.34
    .''
    -1.32
     herself
    -1.31
     Canyon
    -1.30
    .*]{}
    -1.30
    urally
    -1.28
    .“
    -1.27
    POSITIVE LOGITS
    ¥
    3.35
    ¡
    3.25
    Ļª
    3.16
    3.15
        ↵
    3.15
    č↵
    3.15
     ↵
    3.15
    ↵↵
    3.15
    ↵↵
    3.15
    ↵
    3.15
    Activations Density 0.416%

    No Known Activations