© 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 EvalsExportsAPI 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. 11387
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to testing

    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
    47
    +0.13
    0.8%
    361
    +0.13
    0.7%
    186
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.13
    0.07
    361
    +0.13
    0.09
    401
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -4.94
    Ļª
    -4.76
    ĨĴ
    -4.57
    ĥ½
    -4.51
    ĵ
    -4.51
    ħ
    -4.51
    ¼
    -4.43
    Į
    -4.41
    IJ
    -4.39
    ·
    -4.38
    POSITIVE LOGITS
     etc
    2.29
     anyway
    2.25
     runtime
    2.06
     cached
    1.94
    ?).
    1.92
     semantics
    1.84
     parsing
    1.83
     Haskell
    1.79
     JSON
    1.78
     initialization
    1.77
    Activations Density 1.451%

    No Known Activations