© 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. 32138
    Prev
    Next
    INDEX
    Explanations

    medical terminology and specific anatomical references

    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
    321
    +0.15
    0.8%
    350
    +0.13
    0.7%
    330
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.15
    0.04
    86
    +0.13
    0.03
    275
    +0.12
    0.01
    Negative Logits
     generality
    -1.67
    %).
    -1.61
     interest
    -1.59
     gover
    -1.58
    heets
    -1.57
     behalf
    -1.57
    achelor
    -1.45
    igma
    -1.42
     applicability
    -1.42
    >()
    -1.38
    POSITIVE LOGITS
    ellar
    2.03
    µ
    1.94
    utive
    1.89
    uted
    1.83
    ·
    1.64
    Ĺ
    1.61
    arie
    1.60
    oon
    1.58
    arias
    1.57
    ·¸
    1.55
    Activations Density 0.333%

    No Known Activations