© 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. 4-RES-SM
    11. 9972
    Prev
    Next
    INDEX
    Explanations

    phrases that contain 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/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
    156
    +0.35
    2.1%
    307
    +0.17
    1.0%
    137
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.35
    0.05
    10
    +0.17
    0.06
    145
    +0.14
    0.05
    Negative Logits
    tees
    -1.71
    CoV
    -1.70
    Verlag
    -1.64
    "}](#
    -1.64
    \])]{}
    -1.60
    ){#
    -1.56
    microorganisms
    -1.53
    GFR
    -1.53
    Ä
    -1.52
    zon
    -1.52
    POSITIVE LOGITS
     simplest
    2.74
     easiest
    2.71
    oretical
    2.59
     following
    2.50
     reason
    2.46
     same
    2.36
     answer
    2.32
     usual
    2.24
     latter
    2.18
     closest
    2.16
    Activations Density 0.332%

    No Known Activations