© 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 EvalsExportsAPI 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. 27777
    Prev
    Next
    INDEX
    Explanations

    the word "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
    478
    +0.26
    1.5%
    98
    +0.18
    1.0%
    388
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.26
    0.02
    252
    +0.18
    0.02
    98
    +0.12
    0.00
    Negative Logits
    ement
    -1.64
    \].
    -1.47
    vist
    -1.47
    ings
    -1.44
     etc
    -1.41
    jcmm
    -1.36
    }$$
    -1.35
    uity
    -1.33
     Chand
    -1.32
    uve
    -1.32
    POSITIVE LOGITS
     latter
    2.02
    orems
    1.66
     GNU
    1.56
    ureus
    1.55
    reon
    1.53
    gnu
    1.52
     transcript
    1.52
    orin
    1.51
     accompanying
    1.50
    eron
    1.49
    Activations Density 0.065%

    No Known Activations