© 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. 29184
    Prev
    Next
    INDEX
    Explanations

    references to legal or administrative terms related to immigration and asylum processes

    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
    40
    +0.15
    0.8%
    189
    +0.13
    0.7%
    82
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.15
    0.05
    231
    +0.13
    0.04
    495
    +0.12
    0.02
    Negative Logits
     citrate
    -1.57
     granules
    -1.55
     upstairs
    -1.42
     acetate
    -1.42
    Fig
    -1.42
    poons
    -1.39
    oma
    -1.38
    omes
    -1.35
     letters
    -1.34
     downstairs
    -1.32
    POSITIVE LOGITS
    ĻĤ
    2.13
    »¿
    2.09
    Ļª
    1.98
    ĥ½
    1.97
    ĺ
    1.85
    Ľ
    1.84
    Į
    1.83
    ĨĴ
    1.81
    ¿½
    1.78
    ģ
    1.74
    Activations Density 0.276%

    No Known Activations