© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30071
    Prev
    Next
    INDEX
    Explanations

    legal actions and legal terminology related to unpaid wages and employment issues

    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
    68
    +0.19
    1.1%
    159
    +0.17
    1.0%
    479
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.19
    0.14
    95
    +0.17
    0.12
    6
    +0.16
    0.13
    Negative Logits
    ¿½
    -1.89
    incorporated
    -1.58
    nis
    -1.53
     motto
    -1.42
     successor
    -1.41
     competitor
    -1.38
    cedes
    -1.38
    roup
    -1.36
     backdrop
    -1.35
     partnership
    -1.32
    POSITIVE LOGITS
    ively
    1.75
     deaths
    1.62
     lives
    1.50
    py
    1.50
    pp
    1.41
    earth
    1.39
    aph
    1.38
     Earth
    1.38
     potentials
    1.38
    ologically
    1.35
    Activations Density 5.357%

    No Known Activations