© 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. 2-RES-SM
    11. 10584
    Prev
    Next
    INDEX
    Explanations

    expressions of dissatisfaction or negativity

    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
    56
    +0.12
    0.7%
    478
    +0.11
    0.6%
    70
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.12
    0.20
    56
    +0.11
    -0.07
    390
    +0.11
    0.05
    Negative Logits
     Legislative
    -1.68
     simultaneous
    -1.63
     delegates
    -1.56
     ÂŃ
    -1.56
     —
    -1.54
     unprecedented
    -1.53
     Convention
    -1.50
     Coron
    -1.48
     Regulation
    -1.46
     Speaker
    -1.43
    POSITIVE LOGITS
     crap
    2.01
    ******
    1.94
     dont
    1.93
     ich
    1.91
     lol
    1.90
    Anyway
    1.87
     didnt
    1.86
     :(
    1.86
    !!!!
    1.85
     alot
    1.84
    Activations Density 8.458%

    No Known Activations