© 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. 13623
    Prev
    Next
    INDEX
    Explanations

    code-related elements and file references in programming contexts

    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
    306
    +0.15
    0.8%
    307
    +0.13
    0.7%
    473
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.15
    0.03
    123
    +0.13
    0.04
    312
    +0.12
    0.03
    Negative Logits
    ?’
    -1.74
    ries
    -1.71
    ually
    -1.66
    aneously
    -1.62
    '">
    -1.62
     incident
    -1.61
    plasty
    -1.55
     sclerosis
    -1.54
    hei
    -1.51
    cott
    -1.49
    POSITIVE LOGITS
    ¶
    6.19
    »
    6.05
    Ĥ
    6.03
    ĨĴ
    5.99
    ·
    5.95
    IJ
    5.95
    ¸
    5.94
    ĥ½
    5.93
    ½
    5.92
    ¼
    5.92
    Activations Density 0.145%

    No Known Activations