© 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. 13846
    Prev
    Next
    INDEX
    Explanations

    technical specifications and recommendations related to products or 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
    156
    +0.13
    0.7%
    483
    +0.12
    0.7%
    481
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.13
    0.07
    368
    +0.12
    0.02
    124
    +0.11
    0.06
    Negative Logits
    ĨĴ
    -3.64
    ¸
    -3.56
    ª
    -3.55
    Ļª
    -3.53
    ·
    -3.52
    Ļ
    -3.52
    Į
    -3.36
    ↵
    -3.35
    ↵
    -3.35
    -3.35
    POSITIVE LOGITS
     purposes
    4.54
     sake
    3.47
     reasons
    2.60
     purpose
    2.40
    pur
    2.10
     emergencies
    2.08
     needs
    2.03
    purpose
    1.98
     applications
    1.89
     convenience
    1.83
    Activations Density 1.355%

    No Known Activations