© 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. 1-RES-SM
    11. 27696
    Prev
    Next
    INDEX
    Explanations

    references to children within 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/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
    156
    +0.20
    1.2%
    507
    +0.13
    0.8%
    87
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.20
    0.04
    445
    +0.13
    0.03
    494
    +0.12
    0.03
    Negative Logits
     ↵
    -3.29
    -3.29
    <|outofrange|>
    -3.29
    -3.29
              ↵
    -3.29
             ↵
    -3.29
    ↵↵
    -3.29
    ↵↵
    -3.29
    č↵č↵
    -3.29
    č↵
    -3.29
    POSITIVE LOGITS
    hoe
    1.96
    kin
    1.64
    iscus
    1.57
    chitz
    1.51
    hood
    1.45
    icides
    1.42
    's
    1.40
    imes
    1.39
     Stanley
    1.39
    chin
    1.37
    Activations Density 0.191%

    No Known Activations