© 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. 28276
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "the" in various contexts

    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
    156
    +0.33
    1.9%
    478
    +0.17
    1.0%
    507
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.33
    0.09
    441
    +0.17
    0.04
    291
    +0.14
    0.09
    Negative Logits
    strom
    -1.80
    "}](#
    -1.58
    ieties
    -1.52
    eder
    -1.51
    âĢIJ
    -1.42
     aberr
    -1.42
    etes
    -1.41
    cule
    -1.40
    upgreek
    -1.40
    åĵģ
    -1.40
    POSITIVE LOGITS
    ĻĤ
    2.30
     same
    2.30
     whole
    2.18
     nice
    2.10
     likes
    2.01
     entire
    2.00
     simplest
    1.94
     easiest
    1.92
     slightest
    1.90
     latter
    1.88
    Activations Density 0.615%

    No Known Activations