© 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. 10501
    Prev
    Next
    INDEX
    Explanations

    complex numerical data and formatting

    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
    348
    +0.40
    2.9%
    156
    +0.21
    1.5%
    25
    +0.14
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.40
    0.13
    172
    +0.21
    0.11
    266
    +0.14
    0.06
    Negative Logits
    oplan
    -1.32
     divided
    -1.28
     subdiv
    -1.20
    .[@
    -1.20
    ,[@
    -1.17
    ↵↵↵↵↵↵↵
    -1.15
    )](#
    -1.15
     commune
    -1.14
    ↵
    -1.12
    igen
    -1.11
    POSITIVE LOGITS
    ĻĤ
    3.00
    ©
    2.95
    ĨĴ
    2.78
    ¯
    2.73
    Ļ
    2.70
    Īĺ
    2.70
    §
    2.64
    ³
    2.55
    ·
    2.55
    Ļª
    2.53
    Activations Density 6.926%

    No Known Activations