© 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. 9962
    Prev
    Next
    INDEX
    Explanations

    references to hydro-related topics or terms

    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
    248
    +0.15
    0.8%
    21
    +0.14
    0.8%
    98
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.15
    0.01
    98
    +0.14
    0.01
    130
    +0.13
    0.01
    Negative Logits
    ivity
    -1.83
    ableness
    -1.73
    abouts
    -1.69
     yours
    -1.63
     Caption
    -1.57
    iginally
    -1.56
    oddsidemargin
    -1.52
     minds
    -1.46
    nier
    -1.44
    izumab
    -1.44
    POSITIVE LOGITS
    ·¸
    3.17
    µ
    3.01
    ·
    3.01
    Ł
    2.98
    º
    2.96
    Ľ
    2.83
    ³
    2.79
    ¼
    2.77
    ł
    2.72
    »
    2.70
    Activations Density 0.035%

    No Known Activations