© 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. 2-RES-SM
    11. 10140
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and experiences

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    478
    +0.17
    1.0%
    410
    +0.14
    0.8%
    369
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.17
    0.08
    301
    +0.14
    0.10
    81
    +0.13
    0.11
    Negative Logits
    °
    -3.40
    Ħ
    -3.10
    Ļª
    -2.97
    ŀ
    -2.96
    ĸ
    -2.88
    Ģ
    -2.86
    ĻĤ
    -2.80
    ¿½
    -2.79
    Ĥ
    -2.78
    ĥ½
    -2.78
    POSITIVE LOGITS
    brahim
    2.36
    'm
    2.17
     hope
    2.09
     congrat
    2.05
     wonder
    2.04
     confess
    1.96
     apolog
    1.91
    'll
    1.91
     wish
    1.90
    ago
    1.88
    Activations Density 0.560%

    No Known Activations