© 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. 2-RES-SM
    11. 31084
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to RNA and its functions in molecular biology

    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
    156
    +0.22
    1.3%
    502
    +0.12
    0.7%
    426
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.22
    0.01
    162
    +0.12
    0.01
    42
    +0.10
    0.01
    Negative Logits
     resignation
    -1.93
    ]>
    -1.75
     yours
    -1.71
     EEOC
    -1.69
    ĥ½
    -1.69
    itle
    -1.64
     circumstance
    -1.61
     commute
    -1.57
     org
    -1.52
    inois
    -1.52
    POSITIVE LOGITS
    LEY
    1.65
    meg
    1.62
     used
    1.55
     controlled
    1.50
     polymerase
    1.48
     against
    1.43
    IFN
    1.43
    âĪ¼
    1.43
    NG
    1.42
    behind
    1.42
    Activations Density 0.050%

    No Known Activations