© 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. 14059
    Prev
    Next
    INDEX
    Explanations

    terms related to the .NET framework and its components

    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
    34
    +0.15
    0.8%
    146
    +0.14
    0.8%
    226
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.15
    0.03
    34
    +0.14
    0.03
    189
    +0.13
    0.03
    Negative Logits
    ·¸
    -2.54
    ĵ
    -2.37
    ħ
    -2.22
    ¿½
    -2.18
    ¸
    -2.18
    ·
    -2.16
    ¼
    -2.15
    İ
    -2.13
    ĥ½
    -2.11
    µ
    -2.05
    POSITIVE LOGITS
     Framework
    2.48
     MVC
    2.37
     Core
    2.31
     framework
    2.30
    Framework
    1.98
     frameworks
    1.98
     Version
    1.95
    fiddle
    1.90
     controllers
    1.78
     SDK
    1.73
    Activations Density 0.112%

    No Known Activations