© 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. 10403
    Prev
    Next
    INDEX
    Explanations

    information related to astronomical discoveries and planetary characteristics

    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
    30
    +0.13
    0.7%
    300
    +0.12
    0.7%
    326
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.13
    0.16
    454
    +0.12
    0.07
    362
    +0.12
    0.14
    Negative Logits
    Ļª
    -2.63
    ©
    -2.42
    §
    -2.39
    ²
    -2.35
    ¦
    -2.08
    ¿½
    -2.07
    Ł
    -2.06
    Īĺ
    -2.05
    ª
    -2.05
    ¼
    -1.97
    POSITIVE LOGITS
     Earth
    2.15
     billions
    2.01
     Observatory
    1.96
     mass
    1.90
     Spacewatch
    1.90
     discoveries
    1.89
     spectrometer
    1.86
     buried
    1.85
     thousands
    1.82
     sea
    1.82
    Activations Density 4.797%

    No Known Activations