© 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. 1-RES-SM
    11. 28547
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "International" and its variants in various contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.19
    1.1%
    362
    +0.13
    0.8%
    71
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.19
    0.03
    340
    +0.13
    0.02
    362
    +0.13
    0.02
    Negative Logits
     TRUE
    -1.70
     true
    -1.68
    lessly
    -1.67
     NULL
    -1.63
     acidic
    -1.48
     FALSE
    -1.47
     GABA
    -1.47
     untreated
    -1.46
     nil
    -1.46
     typical
    -1.46
    POSITIVE LOGITS
    ĸ
    3.26
    ķ
    3.19
    »¿
    3.15
    Īĺ
    3.15
    ·¸
    3.14
    º
    3.03
    ĸ´
    3.01
    ¡
    2.94
    Ĭ
    2.92
    ´
    2.91
    Activations Density 0.073%

    No Known Activations