© 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. 27005
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "first" and related ordinal 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/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
    476
    +0.14
    0.8%
    497
    +0.14
    0.8%
    101
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.14
    0.04
    476
    +0.14
    0.06
    170
    +0.12
    0.05
    Negative Logits
    ople
    -1.66
    ter
    -1.57
    ability
    -1.55
    tering
    -1.48
    alth
    -1.47
    util
    -1.37
     based
    -1.37
    Encoding
    -1.36
    rer
    -1.35
    ulation
    -1.34
    POSITIVE LOGITS
    Īĺ
    1.99
    ¨
    1.96
    ŀ
    1.78
     dozen
    1.78
    ĻĤ
    1.71
    hand
    1.69
    ↵
    1.68
    1.68
    č↵
    1.68
     ↵
    1.68
    Activations Density 0.126%

    No Known Activations