© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27161
    Prev
    Next
    INDEX
    Explanations

    terms related to conflict and its implications

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    82
    +0.14
    0.8%
    365
    +0.11
    0.6%
    458
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.14
    0.02
    177
    +0.11
    0.02
    458
    +0.11
    0.02
    Negative Logits
     vez
    -1.92
     educated
    -1.48
     sweat
    -1.47
     Asst
    -1.47
     trustworthy
    -1.46
    kay
    -1.45
     handy
    -1.39
    OUR
    -1.38
     fabulous
    -1.35
     child
    -1.34
    POSITIVE LOGITS
    iator
    2.29
    ially
    1.99
     resolution
    1.97
     zones
    1.92
    oon
    1.89
    ielle
    1.86
    olver
    1.86
    ively
    1.82
     Resolution
    1.81
     situations
    1.80
    Activations Density 0.146%

    No Known Activations