© 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. 29252
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate causation or reasons for events

    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
    450
    +0.14
    0.8%
    191
    +0.12
    0.7%
    125
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.14
    0.03
    191
    +0.12
    0.03
    506
    +0.10
    0.02
    Negative Logits
    ¢
    -3.25
    ĨĴ
    -3.11
    Ļª
    -3.10
    Ń
    -3.05
    ij
    -3.04
    Ľ
    -3.02
    º
    -3.01
    Ĥ¬
    -2.88
    ĭ
    -2.87
    ŀ
    -2.82
    POSITIVE LOGITS
    vere
    1.78
    iment
    1.67
    initis
    1.63
     regard
    1.38
    tons
    1.38
    iments
    1.36
    uden
    1.35
    idden
    1.35
    forth
    1.33
     consequences
    1.32
    Activations Density 0.094%

    No Known Activations