© 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. 4-RES-SM
    11. 12129
    Prev
    Next
    INDEX
    Explanations

    discussions about project requirements for 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/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
    307
    +0.22
    1.3%
    476
    +0.18
    1.0%
    263
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.22
    0.10
    390
    +0.18
    0.11
    379
    +0.12
    0.08
    Negative Logits
    Ļª
    -4.32
    į
    -4.29
    Į
    -4.22
    »¿
    -4.15
    Ĩ
    -4.11
    ¢
    -4.05
    ij
    -4.05
    ¤
    -4.03
    -4.01
    ↵↵↵
    -4.01
    POSITIVE LOGITS
     tutorials
    2.26
     myself
    2.10
     alternatives
    2.03
     someday
    1.99
     frameworks
    1.94
    wiki
    1.92
     plugins
    1.88
     please
    1.83
     libraries
    1.82
     solutions
    1.82
    Activations Density 1.283%

    No Known Activations