© 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. 9108
    Prev
    Next
    INDEX
    Explanations

    elements related to game organization and structure

    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
    307
    +0.36
    2.2%
    235
    +0.15
    0.9%
    306
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.36
    0.24
    466
    +0.15
    0.18
    306
    +0.14
    0.07
    Negative Logits
    thems
    -1.96
    liness
    -1.54
     respectively
    -1.50
     counterparts
    -1.46
     leurs
    -1.39
    bands
    -1.37
     uniforms
    -1.36
    ometers
    -1.35
     Their
    -1.34
     themselves
    -1.34
    POSITIVE LOGITS
    ĥ½
    2.89
    ±
    2.64
    ↵
    2.58
    2.58
    2.58
    ↵↵
    2.58
    ↵
    2.58
    ↵
    2.58
    č↵
    2.58
    2.58
    Activations Density 5.629%

    No Known Activations