© 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. 13263
    Prev
    Next
    INDEX
    Explanations

    keywords specific to programming and technical terminology

    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
    21
    +0.29
    1.7%
    209
    +0.12
    0.7%
    283
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.29
    0.07
    255
    +0.12
    -0.00
    98
    +0.11
    0.02
    Negative Logits
    ĨĴ
    -1.72
    Ļª
    -1.72
    ĻĤ
    -1.57
    ruck
    -1.57
    wagen
    -1.51
    dule
    -1.51
    pered
    -1.48
    uated
    -1.48
    »¿
    -1.46
    ı
    -1.43
    POSITIVE LOGITS
    is
    3.29
    IS
    2.63
    isi
    2.19
    Is
    2.05
    isia
    2.01
    ises
    2.01
    isf
    2.00
    isel
    2.00
    isle
    1.98
    isco
    1.98
    Activations Density 0.570%

    No Known Activations