© 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. 4-RES-SM
    11. 12235
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational development and education

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    402
    +0.14
    0.8%
    154
    +0.11
    0.6%
    9
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.14
    0.11
    418
    +0.11
    0.06
    145
    +0.11
    0.07
    Negative Logits
    opically
    -1.56
    ftime
    -1.54
    ither
    -1.47
    inally
    -1.44
    amycin
    -1.43
    ioned
    -1.42
    orem
    -1.41
    })}{
    -1.40
    ificantly
    -1.40
    transformed
    -1.37
    POSITIVE LOGITS
     Association
    3.32
     Authority
    3.31
     Committee
    3.17
     Agency
    3.06
     Manager
    3.01
     Center
    3.01
     Services
    2.95
     Facility
    2.90
     Initiative
    2.87
     Unit
    2.84
    Activations Density 0.951%

    No Known Activations