© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11596
    Prev
    Next
    INDEX
    Explanations

    events or milestones related to awards and recognitions

    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
    350
    +0.14
    0.8%
    263
    +0.13
    0.7%
    319
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.14
    0.04
    132
    +0.13
    0.06
    485
    +0.11
    0.03
    Negative Logits
    ĻĤ
    -4.91
    º
    -4.25
    ¶
    -4.21
    Ļª
    -4.19
    ¹
    -4.13
    ĩ
    -4.13
    ¯
    -4.07
    Ķ
    -4.05
    ¦
    -4.05
    £
    -4.02
    POSITIVE LOGITS
     anniversary
    2.48
     unprecedented
    2.30
     premiere
    2.18
     milestone
    2.08
     legendary
    2.08
     comeback
    2.04
     inaugural
    2.02
     victory
    1.96
     debut
    1.95
     epic
    1.89
    Activations Density 1.201%

    No Known Activations