© 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. 28187
    Prev
    Next
    INDEX
    Explanations

    specific terms related to parenting support and childbirth resources

    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
    +0.18
    1.0%
    17
    +0.12
    0.7%
    11
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.18
    0.31
    156
    +0.12
    0.17
    61
    +0.11
    0.24
    Negative Logits
     ${
    -1.71
    ${
    -1.71
    pgen
    -1.66
    ↵
    -1.62
    ppat
    -1.59
     mer
    -1.57
     curative
    -1.47
    ]{}]{}
    -1.40
    .[@
    -1.40
     [$
    -1.39
    POSITIVE LOGITS
    ¼
    2.76
    Ļ
    2.59
    Ħ
    2.34
    ¾
    2.18
    ¿
    2.17
    ¯
    2.14
    ĭ
    2.09
    ĥ
    2.03
    ¢
    2.02
    ®
    2.02
    Activations Density 1.159%

    No Known Activations