© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30253
    Prev
    Next
    INDEX
    Explanations

    references to tuberculosis and related 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
    156
    +0.20
    1.2%
    397
    +0.15
    0.9%
    304
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.20
    0.02
    56
    +0.15
    -0.01
    413
    +0.11
    0.00
    Negative Logits
    Ŀ
    -2.41
    ¾
    -2.34
    ĺ
    -2.31
    ¦
    -2.23
    Ĥ¬
    -2.15
    ī
    -2.14
    ħ
    -2.04
    ®
    -2.04
    §
    -1.97
    ±
    -1.96
    POSITIVE LOGITS
    ](
    1.63
    acillus
    1.60
    enic
    1.59
    acter
    1.55
    istan
    1.54
     \-
    1.53
    NY
    1.46
     aeruginosa
    1.45
    WV
    1.45
    ulic
    1.45
    Activations Density 0.175%

    No Known Activations