© 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. 4-RES-SM
    11. 11009
    Prev
    Next
    INDEX
    Explanations

    references to different species and their classifications

    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
    117
    +0.14
    0.8%
    124
    +0.11
    0.6%
    165
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.14
    0.04
    442
    +0.11
    0.03
    186
    +0.11
    0.03
    Negative Logits
    ĥ½
    -3.27
    ¿
    -3.25
    ŀ
    -3.15
    ī
    -3.05
    ³
    -3.03
    ĺ
    -2.98
    ľĵ
    -2.97
    Ĥ¬
    -2.94
    ĸ´
    -2.90
    ı
    -2.87
    POSITIVE LOGITS
     richness
    2.65
     inhab
    2.61
     species
    2.50
     extinct
    2.42
     phylogen
    2.32
     genera
    2.27
     abundances
    2.14
     taxa
    2.12
    liest
    2.09
    hip
    2.06
    Activations Density 0.191%

    No Known Activations