© 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. 31757
    Prev
    Next
    INDEX
    Explanations

    mentions of 'ron' and related variations within the context of various subjects

    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
    144
    +0.13
    0.7%
    174
    +0.11
    0.6%
    438
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.13
    0.02
    59
    +0.11
    0.01
    271
    +0.11
    0.00
    Negative Logits
     mind
    -1.68
     adverse
    -1.65
     favor
    -1.56
     little
    -1.50
     inhibitory
    -1.47
     other
    -1.45
     favour
    -1.41
     Conclusions
    -1.40
     whatever
    -1.36
     antidepress
    -1.34
    POSITIVE LOGITS
    ®
    2.69
    Ģ
    2.41
    ´
    2.37
    stein
    2.28
    µ
    2.24
    º
    2.18
    nel
    2.18
    nie
    2.17
    stadt
    2.16
    nett
    2.05
    Activations Density 0.150%

    No Known Activations