© 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. 1-RES-SM
    11. 25348
    Prev
    Next
    INDEX
    Explanations

    sentences that start with the definite article "The."

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.50
    3.2%
    111
    +0.21
    1.3%
    478
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.50
    0.10
    156
    +0.21
    0.06
    271
    +0.15
    0.03
    Negative Logits
    ppat
    -1.52
    pgen
    -1.40
    à±ģ
    -1.34
    1451450014514500
    -1.33
    gens
    -1.32
    pcbi
    -1.30
    Parameters
    -1.29
    fficients
    -1.25
    à¨
    -1.24
    pntd
    -1.24
    POSITIVE LOGITS
    Ļ
    1.96
    ¾
    1.94
    Ħ
    1.84
    Ĥ
    1.83
    ĨĴ
    1.65
    ¯
    1.63
    mouth
    1.60
    Ľ
    1.60
    §
    1.58
    ¼
    1.57
    Activations Density 0.270%

    No Known Activations