© 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. 13378
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific experiments and medical assessments

    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
    +0.28
    1.7%
    306
    +0.21
    1.2%
    307
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.28
    0.06
    306
    +0.21
    0.03
    103
    +0.15
    0.03
    Negative Logits
     **
    -2.43
    .[^
    -2.30
    **,
    -2.28
    .**
    -2.24
    **\
    -2.20
     **_
    -2.12
     ([**
    -2.12
    Âł↵
    -2.12
    \.
    -2.11
    .^\[[@
    -2.11
    POSITIVE LOGITS
     +/-
    1.92
     (>
    1.70
     permit
    1.50
     experiments
    1.49
     permitted
    1.44
     reproducibility
    1.40
     studies
    1.38
     specimens
    1.38
     slightest
    1.37
     permitting
    1.35
    Activations Density 1.276%

    No Known Activations