© 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. 4-RES-SM
    11. 13521
    Prev
    Next
    INDEX
    Explanations

    components and properties related to user interface elements

    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
    240
    +0.17
    0.9%
    76
    +0.12
    0.7%
    172
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.17
    0.04
    111
    +0.12
    0.04
    271
    +0.12
    -0.00
    Negative Logits
     Osw
    -1.93
     semen
    -1.82
     Zimbabwe
    -1.75
     Hoover
    -1.69
     Zhou
    -1.66
    YPT
    -1.65
    semin
    -1.59
     veter
    -1.59
    ospor
    -1.57
     Lon
    -1.57
    POSITIVE LOGITS
     React
    3.95
    react
    3.14
     react
    3.08
     props
    2.70
     npm
    2.62
    props
    2.51
     Angular
    2.44
    Component
    2.40
     Component
    2.38
    vue
    2.32
    Activations Density 0.614%

    No Known Activations