© 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. 12550
    Prev
    Next
    INDEX
    Explanations

    subcategories related to various topics

    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
    366
    +0.13
    0.7%
    15
    +0.13
    0.7%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.13
    0.03
    470
    +0.13
    0.03
    366
    +0.12
    0.02
    Negative Logits
     sake
    -1.67
    ESULT
    -1.51
    fully
    -1.47
    undy
    -1.40
    ETHOD
    -1.39
     convenience
    -1.36
    EventArgs
    -1.32
    ibrary
    -1.32
     Heights
    -1.29
     impart
    -1.29
    POSITIVE LOGITS
    Ĥ
    4.21
    ·¸
    4.19
    ł
    4.06
    Ĵ
    4.02
    ı
    4.01
    ¿
    3.95
    ¼
    3.94
    ľ
    3.93
    Ļª
    3.87
    ĸ´
    3.81
    Activations Density 0.027%

    No Known Activations