© 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. 29362
    Prev
    Next
    INDEX
    Explanations

    phrases indicating economic or political significance

    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
    49
    +0.14
    0.8%
    129
    +0.12
    0.6%
    215
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.01
    23
    +0.12
    0.01
    266
    +0.11
    0.01
    Negative Logits
    adeon
    -1.54
     patent
    -1.45
     Norris
    -1.45
     NIH
    -1.45
    ortex
    -1.42
     hypox
    -1.41
    rosophila
    -1.38
     also
    -1.38
     LINEAR
    -1.37
    aped
    -1.35
    POSITIVE LOGITS
    §
    2.83
    ·¸
    2.74
    ¿½
    2.65
    «
    2.62
    ¶
    2.45
    µ
    2.38
    »
    2.38
    ¾
    2.33
    ¢
    2.32
    ¤
    2.31
    Activations Density 0.003%

    No Known Activations