© 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. 12301
    Prev
    Next
    INDEX
    Explanations

    coding-related syntax and structures

    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
    320
    +0.16
    0.9%
    170
    +0.14
    0.9%
    240
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.16
    0.04
    157
    +0.14
    0.24
    47
    +0.14
    0.23
    Negative Logits
    aspx
    -1.68
    endas
    -1.62
    ?’
    -1.60
    eron
    -1.56
    details
    -1.55
    onia
    -1.49
    artments
    -1.49
    rique
    -1.48
    TeX
    -1.45
    pages
    -1.45
    POSITIVE LOGITS
     _
    1.60
     /*!<
    1.49
     heartbeat
    1.48
    ↵↵	
    1.43
     assert
    1.42
     hub
    1.42
     fmt
    1.41
     //!
    1.41
    ↵↵		
    1.39
    amsbsy
    1.39
    Activations Density 7.098%

    No Known Activations