© 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. 10157
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology 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/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
    +0.40
    2.5%
    21
    +0.26
    1.6%
    50
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.40
    0.08
    78
    +0.26
    -0.01
    17
    +0.11
    0.06
    Negative Logits
    <|outofrange|>
    -2.95
    ↵
    -2.95
    <|outofrange|>
    -2.95
    <|outofrange|>
    -2.95
    -2.95
    ↵
    -2.95
    -2.95
    <|outofrange|>
    -2.95
    <|padding|>
    -2.95
    ↵
    -2.95
    POSITIVE LOGITS
     APIs
    2.10
     API
    1.91
    unsafe
    1.88
     interfaces
    1.87
     unsafe
    1.85
     async
    1.82
     namespace
    1.80
     constructor
    1.79
     interface
    1.78
     uintptr
    1.77
    Activations Density 1.572%

    No Known Activations