© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 14409
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws and regulations concerning the possession of items

    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
    21
    +0.24
    1.5%
    306
    +0.19
    1.1%
    348
    +0.17
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.24
    0.03
    86
    +0.19
    0.03
    376
    +0.17
    0.01
    Negative Logits
    .[@
    -2.12
    .)
    -2.01
    .^[@
    -2.01
    .”).
    -1.96
    .^\[[@
    -1.94
    .")
    -1.88
    .).
    -1.88
    .").
    -1.87
    .),
    -1.86
    ^)
    -1.79
    POSITIVE LOGITS
     myself
    1.47
     solely
    1.25
     NOT
    1.22
     primarily
    1.20
     uniquely
    1.17
     exclusively
    1.16
     individually
    1.15
     anywhere
    1.15
     herself
    1.14
     specifically
    1.14
    Activations Density 2.089%

    No Known Activations