© 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. 12373
    Prev
    Next
    INDEX
    Explanations

    references to products and services

    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
    387
    +0.14
    0.8%
    368
    +0.12
    0.6%
    163
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.14
    0.02
    173
    +0.12
    0.04
    387
    +0.11
    0.05
    Negative Logits
    ±
    -3.20
    ĨĴ
    -3.04
    Ļª
    -3.03
    £
    -3.01
    Ŀ
    -2.92
    ij
    -2.74
    ĩ
    -2.69
    Ĺ
    -2.68
    Ł
    -2.67
    Ĵ
    -2.66
    POSITIVE LOGITS
    ivity
    3.10
    ively
    2.64
     manufacturer
    2.21
     manufacturers
    2.18
     manufactured
    2.17
     manufact
    2.14
    ivities
    2.10
     packaging
    2.04
    iveness
    2.04
     warranty
    2.04
    Activations Density 0.431%

    No Known Activations