© 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. 4-RES-SM
    11. 13139
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to social and environmental 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/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
    348
    +0.15
    0.9%
    186
    +0.15
    0.8%
    411
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.15
    0.11
    20
    +0.15
    0.13
    411
    +0.14
    0.12
    Negative Logits
    ether
    -1.85
    unction
    -1.56
    cardia
    -1.52
    tgz
    -1.51
    ](#
    -1.48
     Redistributions
    -1.46
    orrow
    -1.45
    bery
    -1.44
    )](#
    -1.44
    disambiguation
    -1.43
    POSITIVE LOGITS
    ologists
    3.11
     enthusiasts
    3.04
     professionals
    3.02
     managers
    2.94
     executives
    2.86
    ologist
    2.79
     specialists
    2.78
     administrators
    2.78
     engineers
    2.76
    ists
    2.72
    Activations Density 2.380%

    No Known Activations