© 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. 1-RES-SM
    11. 24716
    Prev
    Next
    INDEX
    Explanations

    commands or instructions typically used in programming

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.16
    0.9%
    139
    +0.15
    0.8%
    113
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.16
    0.03
    113
    +0.15
    0.02
    447
    +0.13
    0.02
    Negative Logits
    ³
    -3.62
    »¿
    -3.52
    ¸
    -3.27
    ĥ½
    -3.12
    ĸ
    -3.11
    ½
    -3.05
    ĭ
    -3.05
    ·¸
    -2.98
    ĨĴ
    -2.98
    ĩ
    -2.96
    POSITIVE LOGITS
     processor
    1.76
     prompt
    1.67
     manual
    1.64
    eered
    1.56
    itude
    1.53
    suite
    1.52
    endant
    1.48
    line
    1.48
     typed
    1.47
    finder
    1.46
    Activations Density 0.141%

    No Known Activations