© 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. 2-RES-SM
    11. 26757
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "we" and related ideas involving group activity or collaboration

    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
    +0.39
    2.4%
    418
    +0.12
    0.7%
    263
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.39
    0.00
    389
    +0.12
    0.02
    410
    +0.11
    0.01
    Negative Logits
    itud
    -1.52
    ublic
    -1.50
     expired
    -1.50
    ).[
    -1.39
    inations
    -1.36
    Pub
    -1.34
    resis
    -1.33
    ingu
    -1.32
     '')
    -1.31
    .),
    -1.30
    POSITIVE LOGITS
    Ĥ
    1.64
    ³
    1.58
    ĨĴ
    1.53
    odor
    1.38
     wonders
    1.37
    omorphism
    1.35
     indeed
    1.34
    athering
    1.31
    ª
    1.31
     dependence
    1.31
    Activations Density 0.046%

    No Known Activations