© 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. 4-RES-SM
    11. 10570
    Prev
    Next
    INDEX
    Explanations

    references to users and consumers in various contexts

    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
    348
    +0.15
    0.9%
    21
    +0.12
    0.7%
    156
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    190
    +0.15
    0.09
    162
    +0.12
    0.03
    401
    +0.11
    0.04
    Negative Logits
    ĻĤ
    -3.36
    ĥ½
    -3.04
    ↵
    -2.81
    -2.81
    -2.81
    -2.81
              ↵
    -2.81
    ↵
    -2.81
     ↵
    -2.81
    ↵↵
    -2.81
    POSITIVE LOGITS
     to
    1.89
     liable
    1.85
    can
    1.65
     able
    1.63
     alike
    1.62
    how
    1.57
     accountable
    1.56
     unable
    1.54
     wishing
    1.54
     who
    1.50
    Activations Density 0.885%

    No Known Activations