© 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. 14862
    Prev
    Next
    INDEX
    Explanations

    patterns and structures relating to legal and governmental concepts

    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
    +0.21
    1.3%
    306
    +0.21
    1.3%
    271
    +0.20
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.21
    0.04
    255
    +0.21
    -0.01
    203
    +0.20
    0.04
    Negative Logits
    aneously
    -1.89
    ially
    -1.86
    iously
    -1.78
    istically
    -1.74
    ively
    -1.68
    fully
    -1.59
    ardless
    -1.58
    prisingly
    -1.57
    iginally
    -1.56
    grily
    -1.52
    POSITIVE LOGITS
    Ĵ
    4.23
    ĥ½
    4.21
    ¡
    4.16
    ³
    4.13
    £
    4.08
    ↵
    4.00
    4.00
    4.00
    4.00
    4.00
    Activations Density 0.792%

    No Known Activations