© 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. 9454
    Prev
    Next
    INDEX
    Explanations

    script headers and commands in coding syntax

    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
    156
    +0.29
    1.6%
    271
    +0.15
    0.8%
    490
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.29
    0.01
    460
    +0.15
    0.01
    350
    +0.13
    0.01
    Negative Logits
    ypse
    -1.46
     attract
    -1.44
     urge
    -1.40
     Tonight
    -1.38
     bear
    -1.37
     Clinic
    -1.36
     Mayo
    -1.32
     movements
    -1.31
     Dublin
    -1.31
     attracting
    -1.30
    POSITIVE LOGITS
    §
    3.31
    ĭ
    3.17
    ½
    3.11
    Į
    3.08
    İ
    3.03
    ĨĴ
    2.92
    ¿
    2.85
    ¬
    2.71
    ·¸
    2.70
    ª
    2.64
    Activations Density 0.042%

    No Known Activations