© 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. 10010
    Prev
    Next
    INDEX
    Explanations

    themes related to family, love, and the human experience across generations

    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
    156
    +0.21
    1.2%
    25
    +0.15
    0.8%
    137
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.21
    0.20
    291
    +0.15
    0.11
    145
    +0.14
    0.12
    Negative Logits
    §
    -5.92
    Īĺ
    -5.84
    ĻĤ
    -5.71
    ¡
    -5.63
    Ħ
    -5.60
    Ī
    -5.59
    Ķ
    -5.56
    Ĩ
    -5.55
    ³
    -5.50
    Ĥ
    -5.49
    POSITIVE LOGITS
     epic
    2.35
     narrative
    2.34
     bleak
    2.33
     backdrop
    2.29
     realities
    2.22
     tale
    2.21
     turbulent
    2.21
     era
    2.21
     tragic
    2.19
     narratives
    2.17
    Activations Density 2.741%

    No Known Activations