© 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. 4-RES-SM
    11. 13303
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmacology and medication

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.14
    0.8%
    136
    +0.13
    0.7%
    21
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.02
    174
    +0.13
    0.04
    9
    +0.11
    0.04
    Negative Logits
    nier
    -1.62
    liest
    -1.60
     previous
    -1.54
    legged
    -1.54
    ftware
    -1.45
    ulated
    -1.43
    iginally
    -1.43
    bie
    -1.41
    loaded
    -1.38
     caption
    -1.38
    POSITIVE LOGITS
    Ĩ
    4.21
    Ļ
    4.03
    Ľ
    3.97
    »
    3.92
    ľĵ
    3.77
    ħ
    3.72
    ĩ
    3.68
    ĵ
    3.66
    ĸ
    3.64
    ¤
    3.55
    Activations Density 0.545%

    No Known Activations