© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 30258
    Prev
    Next
    INDEX
    Explanations

    technical terms and codes related to programming or software development

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    323
    +0.14
    0.8%
    442
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.14
    0.13
    442
    +0.12
    0.12
    310
    +0.12
    0.09
    Negative Logits
    Ŀ
    -3.12
    ¦
    -3.07
    Į
    -3.00
    ¶
    -2.96
    ¸
    -2.96
    ¿½
    -2.95
    ģ
    -2.91
    «
    -2.90
    İ
    -2.88
    §
    -2.85
    POSITIVE LOGITS
     rap
    1.40
     recipient
    1.31
     accelerator
    1.28
     spawn
    1.28
     knocking
    1.25
    icle
    1.22
    sty
    1.21
    ite
    1.21
    .).
    1.20
    burn
    1.19
    Activations Density 4.303%

    No Known Activations