© 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. 30893
    Prev
    Next
    INDEX
    Explanations

    references to various factors and considerations regarding employment and people's desires to be their own bosses

    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
    302
    +0.19
    1.1%
    453
    +0.11
    0.6%
    240
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.19
    0.08
    407
    +0.11
    0.07
    198
    +0.11
    0.06
    Negative Logits
    soever
    -2.23
    okia
    -1.84
    ане
    -1.70
    еÑģк
    -1.69
    ãĥ³ãĥĪ
    -1.63
    bourg
    -1.59
    ynn
    -1.55
    irts
    -1.52
    äs
    -1.52
    ала
    -1.52
    POSITIVE LOGITS
     available
    1.82
     duplication
    1.74
     objection
    1.68
     inherent
    1.64
     worth
    1.61
     fault
    1.56
     routes
    1.50
     problem
    1.49
     separating
    1.47
     circulation
    1.46
    Activations Density 1.526%

    No Known Activations