© 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. 1-RES-SM
    11. 26304
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals, particularly in the context of politics or law

    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
    397
    +0.12
    0.6%
    59
    +0.10
    0.6%
    472
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.12
    0.03
    268
    +0.10
    0.03
    472
    +0.10
    0.03
    Negative Logits
    erp
    -1.80
    resis
    -1.73
    ermal
    -1.66
     realise
    -1.62
    a
    -1.61
    oS
    -1.60
    alam
    -1.51
    ĥ
    -1.51
    emp
    -1.50
    o
    -1.47
    POSITIVE LOGITS
    aspberry
    1.86
    és
    1.64
    ificial
    1.61
    unners
    1.50
     affiliations
    1.49
    tees
    1.48
    ings
    1.47
    ship
    1.46
    hood
    1.43
     proposition
    1.42
    Activations Density 0.091%

    No Known Activations