© 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. 13989
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements, specifically numerical values related to sizes, distances, or quantities

    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
    477
    +0.13
    0.7%
    19
    +0.13
    0.7%
    217
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.13
    0.04
    477
    +0.13
    0.05
    307
    +0.11
    0.03
    Negative Logits
    arily
    -1.70
    tered
    -1.69
    aping
    -1.52
    ieur
    -1.51
    opolys
    -1.48
    ocene
    -1.48
    sible
    -1.45
    oured
    -1.44
    eren
    -1.42
    ]{}[
    -1.41
    POSITIVE LOGITS
    Ĵ
    2.44
    ·
    2.06
    Ĭ
    2.03
    º
    2.00
    ¢
    1.99
    ļ
    1.96
    ĭ
    1.96
    Hz
    1.91
    ĸ
    1.88
     Hz
    1.88
    Activations Density 0.148%

    No Known Activations