© 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. 13718
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming code

    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
    369
    +0.16
    0.9%
    78
    +0.16
    0.9%
    397
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.16
    0.04
    296
    +0.16
    0.05
    315
    +0.14
    0.05
    Negative Logits
    hering
    -1.57
    hea
    -1.44
    ively
    -1.42
    dock
    -1.41
    fully
    -1.40
    duly
    -1.40
    selves
    -1.34
    thur
    -1.34
    hern
    -1.34
    ksen
    -1.33
    POSITIVE LOGITS
    İ
    3.11
    ı
    3.07
      ↵
    3.00
    ↵
    2.99
    2.99
    <|outofrange|>
    2.99
    2.99
    ↵
    2.99
    <|outofrange|>
    2.99
    ↵
    2.99
    Activations Density 0.142%

    No Known Activations