© 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. 9793
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named "Susan."

    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
    30
    +0.12
    0.7%
    350
    +0.11
    0.6%
    386
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.12
    0.01
    350
    +0.11
    0.03
    410
    +0.10
    0.03
    Negative Logits
     times
    -1.65
     basis
    -1.62
    ously
    -1.59
     certain
    -1.43
     needed
    -1.39
     otherwise
    -1.36
    raising
    -1.35
    house
    -1.33
    ogi
    -1.33
     healthier
    -1.33
    POSITIVE LOGITS
    ²
    3.90
    ·
    3.75
    «
    3.66
    ¶
    3.62
    º
    3.36
    ¡
    3.27
    ¬
    3.24
    Īĺ
    3.21
    ¾
    3.21
    ľ
    3.19
    Activations Density 0.225%

    No Known Activations