© 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 EvalsExportsAPI 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. 27514
    Prev
    Next
    INDEX
    Explanations

    chemical and anatomical terms related to biology and medicine

    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
    397
    +0.21
    1.2%
    258
    +0.15
    0.9%
    304
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.21
    0.04
    58
    +0.15
    0.04
    304
    +0.12
    0.05
    Negative Logits
    ĵ
    -3.04
    ĺ
    -2.97
    Īĺ
    -2.96
    Ĺ
    -2.94
    Ī
    -2.94
    ¾
    -2.94
    ¦
    -2.86
    Ŀ
    -2.86
    ij
    -2.85
    Ħ
    -2.84
    POSITIVE LOGITS
    uary
    1.82
    icz
    1.79
    esian
    1.79
    wagen
    1.74
     Scotia
    1.73
     thereof
    1.71
    burgh
    1.70
    bery
    1.70
    bourg
    1.70
    insula
    1.64
    Activations Density 0.621%

    No Known Activations