© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 26794
    Prev
    Next
    INDEX
    Explanations

    emotions and reactions related to distress and significant events

    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
    111
    +0.15
    0.8%
    99
    +0.11
    0.6%
    346
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.15
    -0.07
    56
    +0.11
    -0.07
    394
    +0.11
    0.11
    Negative Logits
     '.
    -2.48
    '.
    -2.32
     whilst
    -2.22
     ',
    -2.09
    "."
    -1.88
     '%
    -1.86
     ')
    -1.86
    ".
    -1.86
    ';
    -1.79
    ...'
    -1.75
    POSITIVE LOGITS
    illard
    1.63
    ensing
    1.57
    pull
    1.46
    tech
    1.44
     overhaul
    1.42
     season
    1.36
     chefs
    1.33
     Silicon
    1.32
    aska
    1.30
     franch
    1.29
    Activations Density 4.909%

    No Known Activations