© 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. 12529
    Prev
    Next
    INDEX
    Explanations

    references to specific cell types and biological processes

    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
    21
    +0.24
    1.4%
    416
    +0.12
    0.7%
    321
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.24
    0.02
    386
    +0.12
    0.01
    410
    +0.11
    0.03
    Negative Logits
    heer
    -1.54
     chloride
    -1.33
     restraints
    -1.30
    chain
    -1.28
     chain
    -1.26
     prescriptions
    -1.23
    ings
    -1.22
    fav
    -1.19
    irl
    -1.19
     discontin
    -1.17
    POSITIVE LOGITS
    e
    2.17
    »¿
    1.99
    ey
    1.89
    usc
    1.89
    ¾
    1.81
    us
    1.80
    Ħ
    1.77
    Ĭ
    1.77
    uses
    1.73
    oglob
    1.72
    Activations Density 0.232%

    No Known Activations