© 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. 30037
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and descriptive statistics relating to locations and populations

    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
    212
    +0.15
    0.8%
    40
    +0.15
    0.8%
    167
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.15
    0.03
    165
    +0.15
    0.03
    353
    +0.14
    0.03
    Negative Logits
    Ļª
    -1.94
     accelerator
    -1.57
     script
    -1.51
    ++;
    -1.49
     futures
    -1.45
     skill
    -1.45
     math
    -1.44
     session
    -1.43
     calculator
    -1.42
    defer
    -1.40
    POSITIVE LOGITS
    liness
    1.95
    amycin
    1.61
    Argued
    1.45
     stains
    1.40
     dysplasia
    1.40
    coat
    1.39
     deported
    1.36
    chitz
    1.35
     infections
    1.35
     pronounced
    1.33
    Activations Density 0.317%

    No Known Activations